# Billing & Credits Source: https://docs.memo.solutions/account/billing-and-credits How Memo's credit system works — plans, top-ups, what costs credits, and where to check your balance. Memo uses credits to meter work that involves computation — generation, analysis, and agent chat. Saving, organizing, and browsing are always free. ## Plans | | Free | Studio | Pro | Max | | ------------------------ | -------- | ---------- | ---------- | ----------- | | **Price** | \$0 | \$15/month | \$50/month | \$200/month | | **Credits / month** | 1,000 | 8,000 | 30,000 | 120,000 | | **Seats** | 1 | 1 | 1 | 1 | | **Owned workspaces** | 1 | Unlimited | Unlimited | Unlimited | | **Premium image models** | — | — | ✓ | ✓ | | **Rate limits** | Standard | Higher | Higher | Highest | Annual billing gets you two months free ($150 / $500 / \$2,000 per year). Monthly plan credits reset at each billing cycle — unused monthly credits don't carry over. The full per-model price list lives on [memo.solutions/pricing](https://memo.solutions/pricing). ## Top-ups Need more than your monthly allocation? Credit packs are one-time purchases that **never expire**: | Pack | Price | | --------------- | ----- | | 5,000 credits | \$15 | | 15,000 credits | \$45 | | 25,000 credits | \$72 | | 50,000 credits | \$140 | | 75,000 credits | \$200 | | 100,000 credits | \$260 | Buy them from the credit pill in Studio or **Workspace Settings → Billing**. ## What costs credits * **Image generation** in Studio — from 17 credits per image (Krea 2 Turbo drafts, Muse Image edits at 20); a standard image on the default model is 68. Cost varies by model and quality (1K/2K/4K) * **Video generation** in Studio and the Video tool — cost varies by model, duration, and resolution (a 5-second clip ranges from roughly 750 credits at 480p to 23,000+ at 4K, depending on the model) * **Image analysis** — extracting color palette, composition, style (\~1 credit) * **Agent chat** — varies with the model, conversation length, attached context, and the number of AI calls needed to complete the work Every generation shows its credit price before you run it. The one exception is a reference video on Seedance, whose length is added when you run (see below). Credit deductions are atomic, so the balance can never go below zero. ### Reference fees on video Some video models charge for the references you attach. Memo charges what the model provider charges for your exact references, plus the usual margin. You never pay for a worst case you didn't use. * **MiniMax H3**: the first 5 reference images are free, then a flat fee per extra image. * **MiniMax H3 Max**: reference images are priced by shape. Four square images are free. Wider images count for more, so a 16:9 image counts as nearly two square ones. For a 5-second 768p clip, nine square references add 308 credits and nine widescreen references add 740. * **Seedance 2.0 and 2.5**: a reference video is priced by its length. You pay for your clip's length plus the reference video's length, at 60% of the usual per-second rate. A short reference can make the clip cheaper than using none; a long one costs more. For a 5-second 720p Seedance 2.5 clip, that's 7,095 credits with no reference video, 5,960 with a 2-second reference, and 8,514 with a 5-second one. Memo measures your references when you press **Generate**, holds that exact amount, and charges it when the clip finishes. The price on the Generate button already includes image reference fees. With a reference video on Seedance, it notes that the video's length is added when you run. If a reference file can't be read, the run stops before anything is held or charged. Re-export it as MP4/MOV for video or JPG/PNG for images and try again. ### How chat credits are calculated Memo uses the provider's reported cost for each AI call when available, then applies Memo's markup and rounds up to whole credits. The current minimum is one credit per billable AI call. A single message or creative brief can need several calls; it does not have a fixed per-message price. Image and video generations have their own charges. When the provider reuses previously processed instructions or brand context, the lower cost of that reused input flows through to your chat credits. Creating a cache can cost more on the first call, so savings depend on how much context is reused across later calls. If the provider doesn't report a cost, Memo estimates it from usage and model rates. For supported Claude models, that estimate accounts for both cache reads and cache writes. These efficiencies run automatically while you work on your brief. ## Checking your balance * **Studio**: A credit pill in the header shows your current balance. Hover for a breakdown. * **Workspace Settings → Billing**: Current plan, seat usage, limits, and an upgrade button. When credits are low, pre-action warnings appear before credit-consuming operations. When exhausted, a dedicated upgrade prompt. ## Rate limiting The system enforces per-workspace rate limits to prevent runaway costs: * **Studio chat**: 60 requests/hour on free, 300/hour on Pro * **Generation**: Per-workspace quotas checked before every generation * **Analysis and other endpoints**: Tier-based limits Hit a rate limit and you'll see a clear message. Wait for the window to reset, or upgrade for higher limits. During beta, every workspace has a 20 GB hard storage ceiling. Uploads above it are refused with a clear message, and so are new generations: a generation that would push the workspace past its storage limit is stopped before any credits are held. Deleting a brand asset hides it immediately; Memo keeps the underlying file for 30 days before it is removed for good, so a mistaken delete can be recovered by support during that window. ## Per-project cost tracking Every Studio project tracks its own credit consumption via usage logs. This gives you visibility into what each campaign costs — useful for agencies billing back to clients or teams tracking creative spend. Billing is handled through Stripe — checkout, customer portal, and receipts. Upgrade from **Workspace Settings → Billing**. ## Tips * **Saving inspirations is free.** Build your library without spending credits. * **Analysis results are permanent.** Run it once, see the results forever. No re-charge on revisit. * **The credit exhaustion modal shows your exact balance** and what you need to continue. No guessing. # Security Source: https://docs.memo.solutions/account/security Turn on two-factor authentication so every sign-in asks for a code from your authenticator app. Two-factor authentication adds a second step at sign-in: your password, then a six-digit code from an authenticator app on your phone (1Password, Google Authenticator, Authy, or any app that supports time-based codes). ## Turn it on 1. Open **Settings** from the workspace menu and choose **Security**. 2. Click **Turn on**. 3. Scan the QR code with your authenticator app. If you can't scan, enter the setup key shown next to it by hand. 4. Type the six-digit code the app shows and click **Verify and turn on**. From the next sign-in, Memo asks for a code after your password. This applies to Google sign-in too. ## Signing in with a code After your password (or Google), Memo shows a **Two-factor code** screen. Enter the current code from your app. Codes change every 30 seconds; if one is rejected, wait for the next one. ## Turn it off Open **Security**, click **Turn off**, and enter a current code to confirm. ## Lost your device? Two-factor cannot be bypassed from the sign-in screen. Ask another admin of your workspace to remove the factor for you, then set it up again on your new device. ## Admins Memo's admin area can require two-factor for every admin. Once it does, an admin account without a verified factor cannot open it. # Setting Up Your Brand Source: https://docs.memo.solutions/brand-kits/setting-up-your-brand Encode your brand's voice, visual DNA, and creative boundaries into a Brand Kit — so the system carries the context, not you. A Brand Kit tells Memo's agents who your brand is. Colors, fonts, reference images, guidelines — encoded once, applied everywhere. Knowledge should live in systems, not people. ## Browsing Brand Kits Use **List / Grid** in the Brand Kits overview. List uses the same rows as Collections, with a thumbnail, kit name, asset count, readable updated date and an arrow to open the kit. The row menu retains **Delete** when your role permits it. The creation row uses the same layout. Your browser remembers the choice across Brand Kits and the reference asset sections. ## Where Brand Kits live Open **Assets** from the sidebar. This is where every brand kit, asset, and skill lives across your workspace: * **Brand Kits** — grouped identity, guidance, collections, rules, and skills * **Characters, Images, and Videos** — reusable references available to Studio and your connected agent * **Skill library** — reusable creative recipes, including general skills, brand skills and Memo starters. See [Skills](/studio/skills) * **Workspace rules** — requirements shared across brands Open any kit to see and edit its full detail — assets, colors, fonts, and voice & rules. ## Creating a Brand Kit From **Assets → Brand Kits**, use the empty-state **Create Brand Kit** action (or the **New Brand Kit** card once the library has content). Give it a name and it's created empty. A kit page has three views: * **Overview** — the brand at a glance: logo variants, palette, typefaces, and the brand guidance rendered as readable cards (with page references back into the brand book). A completeness meter at the top shows what's still missing — each chip jumps straight to the fix. * **Collections** — the kit's images and videos, organized into named groups. **Unfiled** holds assets saved to the kit that haven't been added to a collection, and only appears while it has something in it. * **Guidance & skills** — the brand's Do / Don't rules, inherited workspace guidance and reusable playbooks in one place. Rules are plain sentences. Only narrower subject or collection conditions and inherited sources need a label. Skills provide procedures for particular tasks. Open the kit to configure: * **Logo** — the kit's primary visual identifier, used throughout Memo surfaces * **Assets** — reference images that represent your visual style (logos, product shots, style references, typography samples) * **Colors** — your brand palette, with near-duplicate dedup and neutral filtering built in * **Fonts** — your typography preferences, deduplicated and capped * **Voice & Rules** — a single free-text document describing your brand's voice, personality, banned language, audience, and hard rules. Markdown-friendly, no fixed structure. Write it the way you'd explain your brand to a new hire. ### Kit thumbnail The picture a kit shows in the **Brand Kits** grid. Set it from the kit page by choosing the image beside the kit's name, or from the kit card's **⋯ → Set thumbnail**. Until you set one, the card previews the kit's own assets. ## Filing assets into a kit From an asset's menu in **Characters**, **Images**, or **Videos**, choose **Add to collection**. The same navigator is available from Inspirations and generated results. Select **General collections** or a **Brand Kit** on the left, then check the collections on the right. Each checkbox saves immediately, and you can select collections in several destinations. **New collection** creates one in the destination you are viewing and adds the item. Choose **Done** to close. Logos go to **Overview → Logo**. Product images, style references, characters, graphic elements, photography, and videos can live in collections. Filing preserves the asset's type and reuses the existing asset; it does not make a second media copy. Kit-owned images and videos leave the general library view once filed. In the kit’s **Collections** overview, use **List / Grid** to choose landscape previews or compact rows with asset counts and creation dates. This uses the same card family as general Collections and Studio. Newest collections appear first after **New collection** (and **Unfiled**, when it has assets). Memo remembers the Brand Kit collection layout independently of Studio, Workflows and general Collections. Inside a collection, **Add assets** lets you choose library images and videos or **Upload images**. In **Unfiled** or an existing collection, open the asset’s menu and choose **Add to collection** to organize it. Open an asset to see its details; videos open with playback controls. Editors can update details, and viewers can inspect them. **Remove from collection** unlinks the asset. It remains in any other collections, or returns to **Unfiled** when its last collection membership is removed. Deleting a collection follows the same rule; it does not delete the underlying media. Organizing assets does not automatically attach every collection member to a generation. Videos saved here are available for browsing and playback; saving a video does not make it an image reference for the AI. ## Voice & Rules The Voice & Rules editor remains one free-text document per kit for background, voice and creative direction. Put requirements that must be checked for every applicable task into the separate rules in **Guidance & skills**, so their scope and priority can be inspected. When you @mention a brand kit in Studio, the agent reads your Voice & Rules alongside your colors, fonts, and reference images. Write what matters. Skip what doesn't. Examples of the kinds of things worth writing here: * **Voice qualities** — "warm but precise, never cute" * **Banned language** — "no em-dashes, no 'unleash', no 'revolutionary'" * **Audience cues** — "we write for founders, not marketers" * **Visual rules** — "always natural lighting, never stock photo aesthetics" * **Product background** — the product range, materials and distinguishing features A short auto-generated summary is also stored alongside the full text. The summary is what travels into the agent's ambient context on every generation; the full text loads when you @mention the kit. This keeps short prompts lean and long prompts rich. ## Workspace rules **Assets → Workspace rules** holds agency-wide requirements. Unscoped rules apply across brands; subject or collection conditions narrow applicability. Keep this set small and use it for requirements that genuinely apply throughout the workspace. ## Collection rules Open any collection inside a Brand Kit and it becomes its own page: a back arrow to the collection grid, the name, a count line, and one **Add assets** action. A toggle switches between **Images** and **Rules**. **Collection rules** use **Do** and **Don't** columns. Keep each rule focused on one requirement. Click its text to edit in a multiline field, then choose **Save rule** or **Cancel**; failed saves retain your text. Long rules expand with **Read full rule**, and narrower scope labels appear as plain text below the sentence. New rules are required by default, so there is no Required or Brand-wide button to configure. Older preferences retain their meaning and a plain Preference label. The agent receives instructions that required rules outrank preferences and more specific guidance wins among equal priorities. This is a precedence policy, not an automatic semantic conflict detector or a guarantee that an image model obeys every constraint. Collection rules apply when the collection is explicitly selected for a task or its referenced assets establish matching context. **Inherited guidance** opens the workspace and brand-wide requirements alongside the collection's own rules. Conditional subject rules are selected from matching references. A rule with both collection and subject conditions can match either condition. Skills live in the workspace or Brand Kit library. The agent chooses a recipe by the task, using its name and use description; there is no skill recommendation control inside collections. Existing skills and references remain saved. Older collection associations no longer affect discovery, and connected agents cannot create new ones. ## Inspecting task context In Studio, select the Brand Kit and choose a collection, **Brand only**, or **From references**. The context preview shows which rules apply, their source, why others are omitted, and why each rule applies. Collection selections reset when you change brand, conversation or workspace; select the intended campaign for the next task. Studio and connected-agent generation use the same rule-selection logic. The final check runs again after the actual references are known, so a selection preview can differ from the final generation context. Required rules are not silently removed to fit the context budget: if they do not fit, generation is blocked before submission and the context must be narrowed or edited. Preferences may be omitted with a visible reason. No preview or authoring check spends generation credits. **Unfiled** never carries rules or skills. It is a holding area, not a product, and it disappears once every asset is in a collection. ## Brand assets Upload reference images and Memo handles the optimization — images over 5MB are automatically resized, JPEG/PNG transparency is detected, and everything is stored at the right resolution. Run analysis on any asset to extract its color palette. The extracted colors are deduplicated (RGB distance \< 18), capped at 12, and saved to your brand palette. You can set any asset as the **default** for its type (one default per type per workspace). ## Characters **Assets → Characters** holds the people and characters you want to appear consistently across generations. Pressing **+** offers two ways in: * **Create a character sheet** — jump to the Character Sheet workflow: give one image of your character and get a full reference pack (turnaround, model sheet, expressions, poses, details), which you can save back to Characters in one click. * **Upload your own** — add one or more images of a character you already have. A character with several images is a **character reference pack**: the first image is the cover, and the card shows a mosaic with the image count. You can add or remove images anytime by opening the character. This is one reusable character asset, separate from the folders called Collections. ## Bring your brand with you (onboarding) Right after you name your first workspace, onboarding asks how your brand should come in. Four doors, one review — nothing is saved until you confirm it: * **Scan your website** — paste your homepage. Memo reads the site's own code (not a screenshot): the colors its stylesheets actually use, the typefaces it loads, the logo from the header, the app icon, the social preview and hero imagery — then follows the main menu into the site's own sections so each becomes a collection, with the copy from every page feeding voice and rules. Takes about 30 seconds and lands in the same review as a brand book. See [Scan your website](#scan-your-website). * **Upload your brand book** — PDF, PNG or JPG, read cover to cover with every printed value verified. See [Auto-extract from a brand book](#auto-extract-from-a-brand-book). * **Import from your AI agent** — Claude, ChatGPT, Cursor or any agent with connector support pushes what it already knows about your brand through Memo's MCP connector. The screen shows the connector URL and a ready-made prompt with your kit's ids baked in, and counts items as they land. See [Connect your agent](/get-started/connect-your-agent). * **Set it up by hand** — logos, colors, fonts, guidance and photography, one screen at a time. After a website scan or brand-book import is saved, onboarding shows what landed and skips straight to the finale — **Fine-tune by hand** walks the manual screens with your imports already in place if you want to adjust anything. Skip and Continue always work; you can import later from the kit page. ## Scan your website Paste a homepage address at the top of the kit's empty state (or in onboarding) and Memo builds a proposed kit from the site itself: * **Colors from the stylesheets.** Every hex is read from the site's CSS character-for-character — the review shows the green **Verified** badge because the value comes from the source, never from a model's reading of a picture. Memo ranks colors by how much the site uses them and by the site's own token names (a `--brand-500` beats a one-off gradient stop), collapses tint ramps into one color per hue, and keeps neutrals separate so a palette of grays can't crowd out the accent. * **Typefaces the site loads** — `@font-face` files, Google Fonts links and named font variables count as strong evidence; system stacks (Helvetica, Segoe UI, -apple-system) are ignored. Fonts loaded from Google Fonts preview in their real face inside the kit. * **The logo** — the header's inline SVG (rasterized, with the site's CSS variables resolved), logo images, and the app icon as the symbol mark. Partner, customer and app-store badges are filtered out. * **Imagery from the whole site.** The homepage's social preview and hero pictures, plus the pictures on each page linked from the main menu — up to six sections, read in parallel. Pictures that repeat across pages (cross-sell cards, badges, a template hero) are treated as site chrome and skipped. * **Collections named the way the site names them.** Every section page becomes a proposed collection under its menu label — "USDA Certified Angus", "Local Angus", "Free-Range Chicken" for a butcher; "Women", "Men", "Sale" for a fashion store — holding the imagery found on that page. Homepage imagery files by type (Editorial, Product…) as before. Rename or uncheck any of them in review; saving creates them in the kit's Collections tab. * **Voice, guidance and rules** — distilled from the copy of every page read, so the guidance's Offer section and the do/don't rules cover the full range, not just the homepage. One fast vision call names and classifies what the parsers found (roughly 15–25 credits; up to about 45 if the backup model has to step in); it can only choose among the values the site actually declares. If a site blocks robots or is a pure JavaScript shell, the scan says so — upload a brand book or continue by hand. ## Auto-extract from a brand book If you already have a brand book PDF (or a brand-guidelines PNG / JPG), drop it onto the **brand book** dropzone in the kit's empty state. Memo reads the whole document — cover to cover — and builds a proposed kit: * **Colors, verified against the book.** Printed hex codes are read from the PDF's own text and double-checked, so what's saved matches the page character-for-character. Verified values show a green badge in review. * **Fonts** with roles (heading, body, display, monospace, accent), weights, and a specimen crop. * **Logos as variants, not repeats.** Each colorway appears once, named the way the book names it ("black on yellow", "light gray on dark"). Co-branding lockups are tagged as lockups, and repeated marks from other pages arrive collapsed behind a "show repeats" toggle. * **Imagery grouped into collections.** Photos and illustrations come pre-filed into named groups — Portraits, Product, Editorial, Illustrations — with short names, treatments, and subject tags. Rename a group or change an image's type to move it; saving creates these as the kit's photo collections. * **Rules, ready to enforce.** Every do/don't from the book's usage pages ("Don't stretch the logo") becomes its own rule, applied to every generation for this brand. * **Brand guidance** — the voice, usage, and photography direction distilled with page citations, shown on the kit's Overview as designed cards. Everything lands in the review modal first — nothing is saved until you confirm. Each item carries a page chip (like `p.12`) that opens the brand book at its source page. Click **Save** and the kit is built: identity, collections, rules, and guidance in one pass. Extraction runs on Memo's accuracy-tier model and is billed in credits at save-quality prices (a typical book runs a few hundred credits, shown before you start). The dropzone accepts PDF, PNG, and JPG up to 20 MB. The brand book itself is stored on the kit, so you can re-open (or re-extract) it later without re-uploading. Connected agents can run the same intake over MCP with their own model — see [Connect your agent](/get-started/connect-your-agent). ## Ambient vs @mention Not all brand context loads automatically. The system distinguishes between: * **Ambient** — workspace rules, a lightweight asset inventory, and active kits' voice summaries are available to Studio chat. This is background context, not a selection of every kit's colors, fonts, and images. * **Selected kit or @mention** — choose a kit in the chat's Brand kit picker, or type `@`, to load its colors, fonts, guidance, rules, and asset catalog. A limited selection of assets is shown as visual context; the entire library is not sent as images. The picker remembers the kit for that conversation; choose **None** for work without a selected kit. Skills are @mention-only. They never run ambiently — you invoke them explicitly. ## Multiple Brand Kits Use separate kits for distinct brand identities, such as different clients or product lines with their own guidelines. Use Studio projects for individual campaigns or films, and collections for grouping references. A project can exist without a Brand Kit. Collections and projects are separate today; naming a collection after a project does not attach it automatically. ## Tips * **Start with assets, not text.** Upload your best reference images and let analysis extract the palette and style. Write the Voice & Rules doc after. * **Keep the Voice & Rules doc specific.** "Use warm, directional lighting" beats "make it look good." Banned words beat positive platitudes. * **The voice summary is auto-maintained.** You edit the full document; Memo summarizes it for ambient context so short prompts stay cheap and long prompts stay rich. # Using Brand Assets in Studio Source: https://docs.memo.solutions/brand-kits/using-brand-assets Choose brand context and reference assets for your Studio work. Select a Brand Kit in Studio chat, or @mention one, to give the agent its identity and guidelines. Brand selection is saved for that conversation. For an independent film or other work without brand guidance, set **Brand kit → None** and attach the individual references you need. Workspace rules and lightweight brand summaries can still be available; None does not create an isolated project library. ## Browsing reference assets In **Assets**, the **Characters**, **Images** and **Videos** sections share the Collections list layout: a thumbnail, name, supporting text and updated date, with the existing actions beside the row. Choose **List / Grid** next to search; that preference is shared with the Brand Kits overview. Image and character rows open their editor. Uploaded video rows retain their video preview and action menu. ## @mentioning a Brand Kit In the Studio chat, type `@` followed by your brand kit name. The agent loads your brand context: > "@Acme Brand — create a hero image for our spring campaign" Mentions appear as styled chips with thumbnails in your message. The agent confirms what it loaded before generating. ## What the agent sees When you @mention a brand kit, the agent gets: * A catalog of linked logos and reference images, with a limited selection shown as visual context * Your defined color palette * Your typography preferences * Your full Voice & Rules document (voice, personality, banned language, audience cues, hard rules) * Any skills associated with the kit, if invoked in the same turn It uses all of this as creative constraints — not decoration. "Always use natural lighting" in your Voice & Rules means the agent won't generate studio-lit shots unless you override. ## Scene references in briefs In a Creative Brief, choose a scene and type `@` to attach an available asset, or use the **+** below the prompt. Its inline chip and thumbnail represent the same scene reference. Removing the thumbnail removes its mentions from that scene; deleting the final inline mention also detaches it. Other scenes keep their selected assets, and the original remains in your library. Reference labels are locked inside prompts. Rename the underlying asset from its own editing surface. Color values such as `#533AFD` display a swatch while keeping the exact value in the generation prompt. See [Creative Briefs](/studio/creative-briefs) for editing, output settings and saved-brief recovery. ## Combining references with brand assets Drag a mood board image onto the canvas and @mention your brand — the agent matches the reference's style while staying within your brand's visual language. Analysis data from the reference (lighting, composition, color) combines with brand constraints (palette, typography, guidelines) to produce work that's both inspired and on-brand. ## How photography is selected The agent receives a catalog of kit photography and selects references for the request. Large catalogs can use photography search. Organizing a kit into collections does not currently restrict this catalog to one campaign's collection. * **Subjects and treatments** — when you save a photo (or auto-extract from a brand book), Memo tags it with subjects ("hands", "product", "skyline") and a treatment ("lifestyle", "product", "detail", "editorial", "portrait"). These power the search. * **Semantic + keyword search** — retrieval blends semantic embedding similarity with keyword matching, so "warm hands holding a mug" finds the close-crop hands shots even if the saved title says nothing about warmth. * **Reference verification** — before generation, the agent verifies the retrieved photos are actually relevant to your prompt. Off-target results are dropped instead of being forced into the output. This is why a well-tagged photo library produces dramatically better generations than a dumping-ground one. Treat tagging as part of the kit setup, not an afterthought. ## Color palette enforcement Named brand colors should retain their exact values in brand design elements. They do not require recoloring skin, scenery, lighting, or wardrobe. State any alternative art direction explicitly. An invoked Skill's explicit palette takes precedence over the kit palette. Using a saved character or product does not by itself request an added logo. Describe where branding should appear when you want it visible. ## Saving generations as brand assets From an image's canvas context menu, **Save to Brand Assets** saves a reusable asset in the workspace. Saving it does not automatically choose a Brand Kit or kit collection. **Add to collection** opens the shared navigator for **General collections** and **Brand Kits**. Choose a destination, then check its collections. Kit collections accept product and style images, characters, graphic elements, photography, and uploaded videos; logos belong in the kit Overview. A collection’s name alone does not connect it to a Studio project or activate its contents as generation context. The system compounds. Generate → save → reference → generate again. Each cycle builds on the last. ## Durable Character sheets From a project's assets page, move a file into **Characters** and choose which Character it belongs to. Memo saves a permanent copy with its own sheet identity and source record. The connected agent can do the same with `promote_character_sheet` after reading the file's current Character-link revision. This permanent sheet survives removal of the source generation. When editing a Character, a stale sheet list cannot silently remove a newly added sheet. Refresh after a conflict, then make your intended edit. Removing a sheet from the refreshed list detaches it from that Character; its source record and permanent copy are retained for recovery. Automatic sheet labels only fill missing descriptions and preserve labels you supplied. # Beta guide Source: https://docs.memo.solutions/get-started/beta-guide What the Memo Professional Beta is, what to try first, where feedback goes, and what happens at day 30. You are one of 20 people in the Memo Professional Beta. This page is the whole deal in one place. ## What the beta is A private beta of Memo, by invitation. The product is in daily use and some edges are still rough. You get a free 30-day window with 30,000 credits. That is roughly 400 images on the default model. Video costs more per clip. Make real work with it, not tests. Your window starts the day your access opens. The end date is shown in the app. ## Four things to try first 1. **Save a few references.** Install the [browser extension](/get-started/browser-extension) and save from any page, or paste a URL into Memo. Ten references are enough to start. 2. **Set up your Brand Kit.** Open **Assets → Brand Kits**. Scan your website, upload a brand book, or set it up by hand. Logo, colors, type, and a few written rules. See [Setting up your brand](/brand-kits/setting-up-your-brand). 3. **Open Studio and describe one image.** Create a project, @mention your Brand Kit in the chat, and describe one real thing you need this week. Then ask for a variation. See [Creating images](/studio/creating-images). 4. **Tell us what happened.** The good, the broken, the confusing. Where it goes is below. When those four work, try a [Skill](/studio/skills) to save an instruction you repeat, and [Inspirations](/save-organize/library) to organize what you saved. ## Where feedback goes * **The Getting Started checklist** (the Memo mark with the progress ring, bottom right in the app) has a Beta section with both weekly forms. Each opens on its day, inside Memo, and ticks the moment you send it. The Week-1 and Week-2 emails lead to the same place. * **The Feedback button** in the app sidebar opens the beta group, this week's form and support. * **Week 1** (day 7): five minutes on what you made, where Memo helped, where it fought you. **Week 2** (day 14): the value and pricing read. Prefer a browser tab? The same forms are at [memo.solutions/f/w1-feedback](https://memo.solutions/f/w1-feedback) and [memo.solutions/f/w2-feedback](https://memo.solutions/f/w2-feedback). * **Something broke:** [support@memo.solutions](mailto:support@memo.solutions). Say what happened and what you expected. Blunt beats polite. Feedback decides what gets fixed next. ## What happens at day 30 Your window ends on the date shown in the app. Nothing is deleted. Your account continues on the Free plan with 1,000 credits a month, and everything you saved and made stays in your workspace. Plans are in **Settings → Billing**. See [Billing & Credits](/account/billing-and-credits). Beta credits are not money. They cannot be refunded or transferred, and they do not carry past the window. ## The proof rule Nothing you make, nothing you say, and neither your name nor your logo is featured publicly without your written approval. Approval is per piece and per place, through the proof-approval form at [memo.solutions/f/proof-approval](https://memo.solutions/f/proof-approval). You approve the exact quote or asset and where it may appear. Nothing else gets used. The [Beta terms](/legal/beta-terms) hold the short legal version. # Browser Extension Source: https://docs.memo.solutions/get-started/browser-extension Install the Memo extension to capture images, screenshots, and links from any website straight into your workspace. The Memo browser extension is the fastest way to put what you find on the web onto your inspiration board — without leaving the page you're on. ## Install The extension is built for Chrome and works on every Chromium-based browser (Brave, Arc, Edge, Opera, Vivaldi). Search for **Memo — Inspiration Board Capture** in the Chrome Web Store, or visit the listing directly from the link in your account. Confirm the permissions dialog. The extension needs broad host permissions because the whole point is capturing from any site you visit — but it only reads pages when you explicitly invoke it. Open the puzzle-piece menu in your browser toolbar and pin Memo so it's always one click away. Open [app.memo.solutions](https://app.memo.solutions) and sign in (or sign up) once. The extension reads your session cookie automatically — there's no separate API key or credentials to copy. ## Capture in three ways **Toolbar popup** — click the Memo icon. Pick a workspace, optionally pick an element on the page (image, video thumbnail, full region), tag it, save. **Right-click** — context menu shortcuts on images, links, and the page itself: * **Add Image to Memo** on any image * **Add Link to Memo** on any link * **Add Page to Memo** on the page background **Keyboard shortcut** — `Cmd+Shift+M` on Mac, `Ctrl+Shift+M` on Windows or Linux. Opens the popup on whatever page you're on. ## What the extension captures * Images from the page (PNG, JPG, GIF, WebP — SVGs are converted to PNG on save) * YouTube and Vimeo thumbnails (auto-detected) * Region screenshots — drag a box around any part of the page * The link itself, with the page title and source URL attached automatically ## What you don't have to fill in Title, description, and source URL are populated from the page you're on. After save, Memo's AI rewrites the title and description into a clean 5–8 word title and a 1–2 sentence summary so your library reads consistently. You only choose **what** to capture, **which tags** to apply, and **which workspace** to send it to. ## Switching workspaces The popup has a workspace dropdown. The extension remembers your last choice and uses it as the default for the next capture. If you don't have edit access to the selected workspace, the **Add to Board** button is disabled and the popup explains why. ## Privacy at a glance * Every request goes only to Memo's own API — no third-party trackers, no analytics, no ad networks. * The element-picker overlay is only injected when you click **Click to Select Element**. It doesn't run while you browse. * Your auth token is stored locally in `chrome.storage.local`, isolated to the extension's origin, and cleared when you sign out from the popup or uninstall the extension. Full details in the [Privacy Policy](/legal/privacy). ## Troubleshooting **The extension button is greyed out.** You're probably signed out. Click the extension icon and sign back in via app.memo.solutions. **The keyboard shortcut doesn't work.** Another extension may have the same shortcut. Open `chrome://extensions/shortcuts` and reassign Memo to a free combination. **Right-click menu doesn't show "Add to Memo".** Refresh the page once after installing — the context menu only attaches on pages loaded after the extension is enabled. **I get a "permission denied" message.** You're trying to save into a workspace where your role is **viewer**. Either switch workspaces in the popup, or ask an admin to upgrade your role. **The popup says my session expired.** Browser cookies were cleared or your session timed out. Open app.memo.solutions, sign back in, and the popup will pick up the new session automatically. # Connect Your Agent Source: https://docs.memo.solutions/get-started/connect-your-agent Give claude.ai, Claude Code, Cursor, or any MCP-compatible agent direct access to your Brand Kits, assets, Skills, Workflows, and on-brand generation. Memo ships a remote MCP (Model Context Protocol) server on every plan — including Free. Connect it once and your AI agent can read your brand, search your assets, run your Workflows, and prepare on-brand image or video generations that only you can confirm. ## Connect The server lives at: ``` https://app.memo.solutions/api/mcp/mcp ``` * **claude.ai**: Settings → Connectors → *Add custom connector* → paste the URL above. * **Claude Code**: `claude mcp add --transport http memo https://app.memo.solutions/api/mcp/mcp` * **Cursor / other MCP clients**: add a remote MCP server with the same URL. The connector uses OAuth — a browser window opens on app.memo.solutions, you approve the connection, and the agent gets scoped access to your workspace. No API keys to copy. Ask your agent *"What's in my brand kit?"* or *"What's my Memo credit balance?"* — if it answers, you're connected. ## What your agent can do Tools are grouped by job: * **Find anything** — one search across your whole workspace by meaning, not keywords: saved inspirations, past generations, and brand assets in a single sweep ("that moody rooftop clip from the summer campaign"). * **Your library** — list your Collections, open one as a visual thumbnail grid right in the chat, read its taste profile and keywords, search every saved image (semantically, once your library is indexed), and read any image's AI analysis and tags. * **Organize the library** — create, rename, and delete Collections; write or refresh a collection's taste profile after reading it; file images into them one by one or in bulk by tag; save new images from URLs, chat uploads, or finished generations — every save is auto-titled and described by AI so it lands searchable. * **Read the brand** — list and read Brand Kits (voice, rules, colors, fonts), semantic search over kit photography and assets. * **Generate** — browse the model catalog with live credit prices, prepare image or video generations, run saved Workflows. Every generation is estimate-first. * **Name and re-find** — generations can carry an agent-chosen name (`label`), and `search_generations` finds past outputs by name or prompt in any later session, ready to reuse as references. * **Skills** — read, create, and update reusable playbooks your team has saved — plus Memo's official starter pack (including the cinema production playbooks: scene testing, acting direction, staging maps, cinematic prompting, and the naming discipline), available read-only in every workspace. * **Build the brand** — create kits, add colors/fonts/rules (scope a rule or a skill to a kit collection with `collection_ids` so it rides only generations that use those assets, mark a rule `strictness: prefer` when it should yield to the prompt; `get_kit_collection` lists what applies), import logos, photography, and characters (including drag-and-drop upload straight from the chat), and promote a finished generation into a named brand asset in one call. * **Read the brand book** — attach a brand guidelines PDF to a kit, read its pages and text layer with the agent's own eyes (printed hex codes and typeface names arrive as ground-truth text), and cut logos and photos straight out of the book into named kit collections. The `brand-book-intake` skill is the full playbook — "set up this brand from the attached guidelines" is a one-ask job. * **Workspace** — check who's signed in, list and create Studio boards, file generations into the right board, see plans and credits. * **Work on the open project** — `get_studio_context` tells the agent which project, brief and scene you have open in Studio and what is selected on the canvas. `create_brief` plans a brief from scratch, `get_brief` reads the whole brief. `update_brief_scene`, `add_brief_scene`, `remove_brief_scene`, `reorder_brief_scenes` and `set_scene_references` change it; `open_brief` and `focus_canvas` move your view; `run_brief` presses Generate on the connected generators after you approve the estimate. ## Work on what you have open When a Studio project is open, the agent knows where you are: the project, the brief and scene in the editor, and the nodes you selected. Say "rewrite this scene" or "make the logo the end frame of scene 3" and the change appears in your open tab within a few seconds, as an undoable edit that autosaves like your own typing. Ask for a whole set, such as two character sheets, a location and a creature, and the agent creates the brief itself, opens it for you and generates only after you approve the estimate. For a one-off image or clip it generates directly, with no brief. If no tab is open, the same edits are applied to the saved project and appear the next time you open it. Opening the editor, focusing nodes and generating need the project open in Memo Studio. If you and the agent change the same scene in the same instant, your tab's version wins and the agent is told. Generation through `run_brief` is estimate-first: the agent shows the scenes and credits, and only starts them after you confirm. The run happens in your open tab from the connected generators, so credit limits and errors show on the canvas exactly as they would if you pressed Generate yourself. ## Manage your Collections from any chat Your inspiration library is fully agent-operable. A few things that work today: * *"What's in our Summer campaign collection?"* — the agent opens it and, in Claude, shows the actual thumbnails inline. * *"Save these 10 URLs into a new Moodboard collection"* — one call ingests, AI-titles, tags, and files them. * *"What's the vibe of the Futurist Glam collection?"* — the agent answers from the collection's taste profile, and writes one if it is missing or stale. * *"Generate three posters from the Futurist Glam collection"* — the taste profile and keywords become the brief for every prompt the agent builds from it. * *"File everything tagged 'outdoor' into Lifestyle"* — bulk filing by tag is a single operation. * *"Which images are still untagged? Clean them up."* — the agent looks at each image itself and writes better titles, descriptions, and tags. Deleting a Collection never deletes images — they stay in your library. Adding images counts against your plan's link limit, same as saving from the extension. Your agent also knows how to keep the library tidy on its own: it sees how many images aren't indexed or filed yet, and it follows built-in housekeeping rules — it does the describing with its own eyes (no Memo credits involved), your own tags are never touched, bulk moves are announced before they happen, and nothing can ever be deleted. In practice: *"tidy up my library"* is a one-line request. None of this machinery appears in your workspace — it lives entirely on the agent's side. ## Name what you make Long-running projects live or die on naming. Two habits keep an agent-driven library organized: 1. **Label keepers at generation time.** Pass `label` (e.g. `product-fw25-sneaker-red-v2`) so the output's title is yours, not an automatic one — labeled outputs are findable by name with `search_generations` next week or next month. 2. **Promote finals into the Brand Kit.** When an output is approved, the agent can save it as a named brand asset (`add_brand_assets` with a `generation_id`) — including as a **character** — so it becomes a permanent, searchable reference the whole team can generate with. ## Credits and safety Generating from an agent costs the **same credits as in the app** — and spending is deliberately two-step: 1. The agent calls `generate_image` / `generate_video` / `run_workflow` and gets back a **priced estimate** naming the destination board. 2. Nothing is spent until `confirm_generation` — the only tool that can spend credits. Agent spending is also capped by a per-workspace monthly budget (30% of your allowance by default), so a runaway agent can never drain your balance. ## Brand rules apply automatically Your kit's do/don't rules ride every agent generation without the agent having to remember them. When the references attached to `generate_image`, `generate_video` or `run_workflow` all belong to one Brand Kit, Memo prepends that kit's rules to the prompt on the server, together with any workspace-wide rules. Workspace-wide rules apply to every generation, references or not. If the references span several kits, only the workspace-wide rules apply and the estimate says so. Rules scale by **subject**. A rule without subjects is kit-wide. A rule with subjects (for example `["Nano Gen 5"]`) rides only when one of the attached reference assets carries that name or subject tag, so product-specific rules never dilute an unrelated render, however many products a kit holds. Set subjects when adding a rule, or later with `update_brand_rules`, which also edits and deletes rules so a kit's list stays short. The estimate and the confirmation both carry a `brandRules` field (`kit`, `applied`, `scoped` for the subject-matched ones, and `omitted` when a very long rule list was trimmed to fit the model's prompt limit), so you can see before spending which rules the model will follow. Rules are prompt guidance: they steer colours, copy, casing and composition well, but they cannot force pixel-exact geometry. For that, keep the truth as a kit asset and a kit skill, and attach the asset as a reference. ## The right skill at the right time Skills can carry subjects too. A skill scoped to `["Nano Gen 5"]` is returned as `suggestedSkills` on the estimate, the confirmation and the completed result whenever the references, or the finished image's own enrichment tags, match, with its trigger hint saying when to run it. The agent no longer has to read every skill summary to find the one that applies. Skills without subjects stay invoke-by-name. ## Where generations land Agent generations file themselves into Studio boards. Estimates name the destination; agents can create a campaign board (`create_project`) or re-file strays (`move_generations`) instead of piling into a shared inbox. Inside a board, `get_project` returns folder counts and descriptions, with one size-limited page of files, and `move_generations` with a `folder_id` files outputs into them — the same folders you see on the project's assets page. `create_project_folder` adds a folder by name (or returns the existing one) and can file generations in the same call. When `move_generations` changes the project, an omitted `folder_id` puts the file in **Unfiled**. Within the same project it keeps the folder. Pass a destination folder explicitly to file it there, or `folder_id: "none"` to unfile it. The response lists the files actually moved and any IDs that were not found in your workspace. `search_generations` can combine a project, media type and `review_status`. Asking for approved files filters the eligible files before selecting the results, so unapproved matches cannot use up the result limit. Name and description matches come first, followed by matches ranked by meaning. A newly named file can be found before its search index catches up. Every generation the agent reads back carries its context: a `description` and `subjects` written from the finished image rather than the prompt, the user's `reviewStatus` when one was set on the canvas (prefer `approved` when several files fit; a missing status is not a rejection — `search_generations` accepts `review_status` to filter), the Character it depicts (`characterAssetId`), and what it was made from (`madeFromGenerationIds`, `madeFromAssetIds`). ## Character reference views When a character has a portrait and additional reference sheets, Memo labels the sent images individually. A portrait, expression sheet and pose sheet keep their own descriptions even when they belong to the same character. This helps the generation model distinguish the purpose of each picture. Choose clear descriptions when saving reference sheets. ## Edit project files safely Ask your connected agent to rename a file, record your review verdict, correct what an image shows, or link it to a Character. For example: “Rename this to Mira — final turnaround, and mark it approved.” A description is reference material; it never grants permission to perform an action. The agent reads `get_generation`, then sends `update_generation` with the revision of each field it changes and a stable `operation_id`. It can change a name while someone else changes a review status. If both change the same field, Memo reports a conflict and saves none of that file's proposed changes. The agent must show the conflict and follow your intended choice. Retrying the same operation ID with the same request returns the original result. Descriptions you or your agent author carry attribution and stay protected from later automatic descriptions. Review attribution records the authenticated user and connected client. Approval always represents an explicit verdict; a model's guess about image quality is not approval. Editor access is required, and writes stop if Memo cannot check the workspace's agent-access policy. ### Find every file in a large project `get_project` provides an overview with folder counts and one globally limited file page. Its response contract is version 2: files are in `filePage.files`, not separate lists repeated inside every folder. Follow `nextFolderAfter` as `folder_after` for more folders, and pass `filePage.nextCursor` to `list_project_files` for more files. `items_per_folder: 0` returns a folder overview without a file page; other values no longer multiply the number of files by the folder count. `list_project_files` supports folder, review status, media type, apparent role, Character, aspect ratio, text query, and missing name/description/folder/identity/provenance/embedding filters. Use `folder_id: "unfiled"` (or `"none"`) for Unfiled. Results are ordered by creation time and ID, so tied timestamps do not lose files. Continue until `hasMore` is false. Cursors belong to one workspace and filter set; start over when changing filters. These tools limit each response's text to 8,000 UTF-8 bytes. A page can contain fewer files than requested to stay within that limit. Labels and descriptions in a list are summaries. `get_generation` returns the current edit revisions; its `prompt`, `description`, and `provenance` sections page through the full text using `nextOffset` and `expected_hash`. Join those pages in order. Pages are not a frozen database snapshot: edits and moves can change which files qualify while you read. Read a file again before editing it. ### Understand what a generation used New stored generation runs capture the final provider request after model-specific settings and reference limits are applied. The run record separates the original creative request, effective settings, requested references, resolved references, images actually sent in their provider slots, and references dropped or unavailable. The provider receipt is recorded separately from the prepared request. Older files without a captured run record say **unknown**. Memo does not reconstruct those inputs from guesses. Inline image bytes are represented by a hash; replay needs the original bytes. Remote files and provider models can change, so even a matching request does not guarantee an identical image. ### Keep Character sheets and repair search `promote_character_sheet` saves a selected completed image as a permanent sheet of an existing workspace Character. It requires the Character-link revision from `get_generation`. The saved sheet has its own ID, permanent copy, and source record, so deleting the source generation does not remove it. Retrying resumes the same copy. A conflict returns the current link and revision; review them before choosing again. Removing a sheet from the Character is a separate explicit edit and retains the source record. `reindex_generations` queues up to 100 authorized file IDs for search repair. It does not run image description or generate media. Indexing and automatic descriptions have separate durable queues. Interrupted work is retried with a lease; stale results cannot replace the index for newer content. Exhausted jobs remain visible for explicit retry. Automatic generation descriptions reserve a monthly workspace allowance before each paid attempt, including retries. A failed or timed-out attempt still uses its reserved slot. If that allowance or its meter is unavailable, Memo makes no description call and uses a local prompt-based name when needed. This is separate from generation credits; names remain editable. # FAQ Source: https://docs.memo.solutions/get-started/faq Answers to the questions we get most often — what Memo is, how it bills, how content is handled, and where to go when something breaks. Memo is an inspiration board paired with a creative agent — you save references from anywhere, encode your brand once, and generate on-brand images and videos in conversation. Designers, creative directors, brand strategists, art buyers, content producers, and small in-house teams that treat references as a discipline. If you're managing a folder of screenshots, a Pinterest board for "later", and a brand book that nobody reads, Memo is the system that ties all three together. **Assets** is the surface in the sidebar. **Brand Kits** live inside it, alongside your brand assets and **Skills**. One brand can have many kits — one per product line, campaign, or client. Skills are where reusable creative playbooks live. Image generation and editing run on state-of-the-art diffusion and multimodal-edit models. Video generation runs on a leading text-to-video model. Chat and analysis run on frontier text and vision models. We pick what works best per task and may swap providers as the field moves — your prompts, kits, and skills are portable across whichever model is in service. You do. To the maximum extent generated content is recognised as ownable under your jurisdiction's law, you keep ownership of every image, video, and output Memo creates from your prompts. Memo only holds the licence it needs to host and display the work for you and your workspace. See the [Terms of Service](/legal/terms-of-service) for the full clause. No. The agent fills in technical detail, asks clarifying questions when a prompt is vague, and pulls your brand kit and references in as context. You provide direction; Memo does the prompt engineering. If you do want full control, switch to **Simple** mode in [Prompt Modes](/studio/prompt-modes). Paid features (generation, analysis, agent chat) are metered in **credits**. Each plan ships with a monthly credit allocation; you can buy top-ups when you need more. Saving inspirations, organizing, browsing, and adding tags are always free. Full breakdown in [Billing & Credits](/account/billing-and-credits). The system blocks credit-consuming actions and shows an upgrade prompt with your exact balance. Free saves and browsing keep working. You can buy a top-up or upgrade your plan from **Workspace Settings → Billing** to keep going. Credit purchases and subscription fees are non-refundable except where required by consumer-protection law in your jurisdiction. If you think you were charged in error, email **[billing@memo.solutions](mailto:billing@memo.solutions)** — we look at every case in good faith. Everything inside it is permanently removed: inspirations, generations, brand kits, Studio projects, chat history, brand book uploads. There is no undo. We confirm twice before performing the delete. If it was your only workspace, your account starts over as new: your next sign-in takes you back through setup from the beginning, and your Getting Started progress resets. Yes. Content is scoped to your workspace and gated by row-level security on the database. Only members of that workspace see it. Memo employees don't browse customer content. No. We don't sell, share, or hand customer content to third parties for AI training. Generation prompts are sent to the model providers we use to actually run the generation, under standard data-processing terms. Either. Many users run a personal workspace as a one-person studio. Every self-serve plan is single-seat today — team seats are on the roadmap. See [Plans](/account/billing-and-credits). Yes. Use the [contact sales form](https://memo.solutions/contact-sales) to share your team size, workflow, and what you want to ship. The Memo team can walk through the product with your own brand, recommend a plan, and discuss rollout, security, or agency needs. The library, search, and tagging work on mobile. Studio (the canvas) requires a desktop-sized screen because the canvas interactions need a real pointer. You'll see an interstitial on phones with a link back to the library. Email **[support@memo.solutions](mailto:support@memo.solutions)** with what you saw, what you expected, and a screenshot if the issue is visual. Feature requests go to the same address. Email **[security@memo.solutions](mailto:security@memo.solutions)** with reproduction steps. Please don't post security issues publicly — we'll respond, fix, and credit you (if you want) after the fix ships. # Quick Start Source: https://docs.memo.solutions/get-started/quick-start From sign-up to your first generated image. Five steps, five minutes. ## 1. Create your workspace After signing up, you'll create a workspace. This is your team's shared container — all inspirations, generations, brand kits, and Studio projects live here. Free, Studio, Pro, and Max are single-seat plans today. One workspace, just you. Shared multi-seat workspaces arrive with the team plans, which come later. See [Members & Roles](/workspaces/members-and-roles) for how workspace access works. ## 2. Save your first inspiration Two ways in: * **Browser extension** — Install it, click the Memo button on any page. The image, source URL, and creator info are captured instantly. The system auto-enriches the title and description in the background. * **Paste a URL** — Drop a link into Memo from your dashboard. Same auto-enrichment, same instant card. Save first, organize later. Don't slow yourself down deciding where things go. Capture liberally, sort in batches. The value of Memo compounds as your library grows. ## 3. Analyze what you saved Open any inspiration card. Switch to the **Analyze** tab and run analysis (\~1 credit). You get back: * Color palette with click-to-copy hex values * Composition breakdown — layout, framing, perspective, depth * Style — medium, aesthetic, era, references * Lighting — type, direction, quality, shadows * Mood, texture, elements, and OCR-extracted text This turns a pretty picture into reusable creative DNA. Copy any section as a prompt, or save the whole thing as a brand asset. ## 4. Open Studio Click **Studio** in the navigation. Create a new project — you land on an infinite canvas with a chat panel on the right. This is your agent. It knows your brand (if you've set one up), it can see your references, and it generates images directly onto the canvas. Type something like: > "Create a minimal product shot of a ceramic mug on a linen tablecloth, soft morning light" The agent refines your prompt and generates. The image appears on your canvas. Ask for variations, edits, or a completely different direction — each iteration is a new node, so you never lose previous versions. ## 5. Set up your brand Onboarding asks how your brand should come in: **scan your website** (paste the homepage, \~30 seconds), **upload your brand book** (PDF), **import from your AI agent** (Claude, ChatGPT, Cursor via the Memo connector), or **set it up by hand**. Both imports land in a review you confirm before anything is saved. Later, from **Assets → Brand Kits**, upload your logo, define brand colors, add typography preferences, and write free-text guidelines ("always use natural lighting," "avoid stock photo aesthetics"). See [Setting up your brand](/brand-kits/setting-up-your-brand). Once configured, @mention your brand kit in any Studio chat: > "@Acme Brand — create a hero image for our spring campaign" The agent loads your colors, logo, typography, and guidelines as creative constraints. Same brain. Every channel. Zero drift. ## Tips for new arrivals * **Install the extension on day one.** It's the fastest way to build a library. * **Analyze the inspirations you love.** An analyzed image becomes reusable — you can copy its lighting as a prompt or save its colors to a Brand Kit. * **@mention a Brand Kit in chat** to anchor every generation to your visual identity. * **Right-click any card** for context actions: add tags, send to space, save as style reference, send to Studio, delete. # What is Memo? Source: https://docs.memo.solutions/get-started/what-is-memo The brand operating system. One brain carrying your voice, visual taste, audience, and strategy — a team of agents that capture, create, and orchestrate on your behalf. Memo is a brand operating system. One brain that carries your voice, your visual DNA, your audience, your strategy. A team of agents that capture, create, and orchestrate on behalf of your brand. Not a content tool. Not a scheduler. Not a better ChatGPT. ## The system Memo has three surfaces that share one brain: * **The Scan** — Drop a URL. The system reads your brand in 30 seconds. * **The Brain** — Voice, visual DNA, personas, pillars, boundaries. The strategic core that every agent draws from. * **The Studio** — Where the work gets made. One idea becomes every format and three variants. Strategy and creativity are not separate jobs here. They share one brain — because in the people who do this work well, they always did. ## Who it's for **Creators** who are tired of context-switching between saving references, building mood boards, and generating work. Your taste compounds here. **Small teams** who want agency-quality output without agency cost. The system carries the context so every piece of work stays on-brand without a 40-page guidelines PDF. **Agencies** running multiple brands who need creative at scale without scaling headcount. Each brand gets its own brain. ## How it works Save visual inspiration from anywhere on the web — browser extension or paste a URL. The system auto-enriches every image with metadata, title, and description. Your library grows with every click. Run analysis on any saved image. Memo extracts the color palette, lighting setup, composition, style references, mood — the full creative DNA. Save those as reusable brand assets. Open Studio. Describe what you want in conversation with an agent that already knows your brand. It generates images and videos on an infinite canvas, using your references and brand kit as creative constraints. Build creative briefs with per-deliverable control. One campaign becomes multiple formats — each with its own aspect ratio, quality, references, and creative direction. The system coordinates. You stay the taste-maker. ## Core vocabulary Memo has a small vocabulary. Learn these and the rest is intuitive: | Term | What it means | | --------------- | -------------------------------------------------------------------------------------------------- | | **Inspiration** | Anything visual you've saved — a screenshot, a photo, a link from the web | | **Generation** | An image or video the system created for you in Studio | | **Collection** | A folder for grouping related inspirations — project mood boards, campaign references | | **Brand Kit** | Your colors, fonts, assets, voice, and rules. The agent uses these to keep work on-brand | | **Skill** | A reusable creative recipe — invoke with a slash command in Studio to run a repeatable workflow | | **Studio** | The canvas + chat agent where you make new work | | **Analysis** | A structured breakdown of an image's visual properties — color, composition, lighting, mood, style | | **Workspace** | Your account container. All inspirations, generations, brand kits, and members live here | | **Credit** | The unit for billing. Generation, analysis, and chat consume credits. Saving is free | ## Start here * [Quick Start](/get-started/quick-start) — from sign-up to your first generation * [Saving from the Web](/save-organize/saving-from-the-web) — build your library * [Studio Overview](/studio/overview) — where the work gets made * [Setting Up Your Brand](/brand-kits/setting-up-your-brand) — encode your strategy # Beta terms Source: https://docs.memo.solutions/legal/beta-terms Draft for founder approval. A short addendum to the Terms of Service for the Memo Professional Beta. **Draft for founder approval.** These beta terms take effect when the founders approve them and the date below is set. *Last updated: draft, September 2026* These beta terms are an addendum to the [Terms of Service](/legal/terms-of-service). They apply to anyone using Memo through the Memo Professional Beta. Everything else stays as written in the Terms of Service and the [Privacy Policy](/legal/privacy). ## As-is The beta is provided as-is. Features may change, break, or be removed during the window. We do not promise uptime, results, or that a feature stays the way you found it. Keep a copy of anything you cannot afford to lose. ## Beta credits Beta credits are not money. They have no cash value. They cannot be refunded, transferred, sold, or exchanged, and they do not carry past the access window. ## Access window Your access window ends on the date shown in the app. On that date your account continues on the Free plan, with the Free plan's credits and limits. Your saved references, Brand Kits, and generations stay in your workspace under the Terms of Service. ## Feedback We may contact you for feedback during the window, by email or in the beta group. Replying is voluntary. During the window, the founders may look at what you generate in Memo, from the admin area, to understand how the product is used and to improve it. Every such view is recorded in an audit log. This is looking, not publishing: the section below still applies in full. ## Your name, your work, your words Nothing you make in Memo, nothing you say about it, and neither your name nor your logo is published, quoted, or featured without your separate written approval. Approval is given per piece and per place, through the proof-approval form at [memo.solutions/f/proof-approval](https://memo.solutions/f/proof-approval), and covers only what it names. ## Everything else The [Terms of Service](/legal/terms-of-service) and [Privacy Policy](/legal/privacy) otherwise apply in full. Where these beta terms and the Terms of Service differ, these beta terms apply for the beta only. Questions: [support@memo.solutions](mailto:support@memo.solutions). # Privacy Policy Source: https://docs.memo.solutions/legal/privacy How Memo handles your data when you use the platform and the Chrome extension. *Last updated: September 21, 2026* This Privacy Policy describes how Memo ("we", "us", or "our") collects, uses, and protects your data when you use the Memo platform at memo.solutions and the Memo — Inspiration Board Capture browser extension. It applies to both the web application and the browser extension. ## What we collect When you use Memo, we collect the following: **Account information** * Email address (used for sign-in and attribution on captures) * Display name and avatar (shown in your workspace alongside content you add) * Authentication tokens (issued by our auth provider when you sign in) **Workspace activity** * Inspirations you save: images, screenshots, links, source URLs, page titles, tags, and notes * Which workspaces you belong to and your role in each (viewer, editor, admin, owner) * Which workspace is currently selected in the extension **Extension-specific data** * Authentication tokens stored locally in your browser via `chrome.storage.local`, used to authorize uploads to your workspace * Your selected environment (production or local development) — used only by developers; defaults to production We do **not** collect: * Your browsing history * Pages you visit while not actively using the extension * Page contents that you do not explicitly capture * Any data from third-party tracking, analytics, or advertising scripts in the extension ## How we use it Your data is used solely to operate the Memo platform: * To authenticate you and authorize uploads to your workspace * To display the inspirations you save back to you and your workspace collaborators * To attribute captures to the user who saved them * To filter, search, and organize your captures using the tags you apply * To respect role-based permissions (e.g. preventing viewers from editing) * To understand how Memo is used and improve it. This can include a founder looking at what you generate, from the admin area. Every such view by staff is recorded in an audit log, and nothing is published or shared without your separate written approval We do not sell your data, share it with advertisers, or use it for any unrelated purpose. ## Where it goes When you save an inspiration: 1. The image (if any) is uploaded to our object storage, hosted by Supabase 2. The metadata (URL, title, tags, your user ID, workspace ID) is written to our Postgres database, also hosted by Supabase 3. All requests are made over HTTPS The data resides in Memo's own infrastructure. We use the following processors to operate the service: * **Supabase** (database, authentication, file storage) — see [Supabase's privacy policy](https://supabase.com/privacy) * **Vercel** (web application hosting) — see [Vercel's privacy policy](https://vercel.com/legal/privacy-policy) * **Stripe** (billing, if you have a paid plan) — see [Stripe's privacy policy](https://stripe.com/privacy) These processors handle data on our behalf under standard data processing agreements. We do not share your data with any third party for their own purposes. ## How long we keep it * **Captures and workspace content**: retained as long as the workspace exists. You can delete individual items, or an entire workspace, at any time from the Memo app. * **Account data**: retained while your account is active. To close your account, use **Delete my account** in Workspace Settings, or email [support@memo.solutions](mailto:support@memo.solutions). Within 30 days of a verified request we permanently remove your account record and de-associate your captures from your identity. * **Extension-local data** (auth token, selected workspace): cleared when you sign out from within the extension popup or when you uninstall the extension. ## Your rights Depending on where you live, you may have rights under data protection laws (such as GDPR in the EU/UK, or CCPA in California), including: * **Access** — request a copy of the data we hold about you * **Correction** — fix inaccurate data * **Deletion** — request that we delete your account and associated data * **Portability** — receive your data in a machine-readable format * **Objection** — object to certain types of processing To exercise any of these rights: account deletion is available in-app (**Workspace Settings → Delete my account**), and a full data export is available at any time from the same settings page (**Export my data**). For access, portability, or anything else, email us at [support@memo.solutions](mailto:support@memo.solutions) — we complete verified requests within 30 days. ### What the export contains **Export my data** downloads a single JSON file with your profile and preferences, plus — for every workspace you own — its settings and members, invites you sent, captures and their collections, generations and the folders they are filed in, projects and their canvases, brand kits (colors, fonts, logos, brand book, photography collections and color palettes), Assets and Workflows, chat history, usage and credit history, and purchase attempts. Payment identifiers, internal cost figures and search indexes are not included. Links to your files inside the export are signed and **stop working 7 days** after the export was made — download anything you want to keep within that window. Each section is capped at 5,000 rows; if a section hit the cap, the app tells you when the download finishes. ## Security * All data is transmitted over TLS (HTTPS) * Database access is gated by row-level security policies that enforce workspace membership and roles * Authentication tokens are stored in `chrome.storage.local`, isolated to the extension's origin and not accessible to web pages * We follow industry standard practices to prevent unauthorized access No system is perfectly secure. If you become aware of a vulnerability, please report it to [security@memo.solutions](mailto:security@memo.solutions). ## Children Memo is intended for users 16 and older. We do not knowingly collect personal data from children under 16. If you believe a child has provided us with personal data, please contact us and we will delete it. ## Changes to this policy We may update this policy from time to time. Material changes will be communicated via email to your registered account, and a notice will appear in the app on your next sign-in. The "Last updated" date at the top of this page is always current. ## Contact Questions, requests, or concerns about your data: * **Email**: [support@memo.solutions](mailto:support@memo.solutions) * **Address**: 251 Little Falls Drive, Wilmington, DE 19808, United States *** *This policy is also available at [memo.solutions/legal/privacy](https://memo.solutions/legal/privacy).* # Terms of Service Source: https://docs.memo.solutions/legal/terms-of-service The terms that govern your use of Memo, including the web application and the browser extension. *Last updated: August 30, 2026* These Terms of Service ("Terms") form a legal agreement between you and Memo ("Memo", "we", "us", or "our") and govern your use of the Memo platform at memo.solutions, the Memo web application, the Memo browser extension, and any related services (together, the "Service"). By creating an account, signing in, installing the extension, or otherwise using the Service, you agree to these Terms. If you don't agree, don't use the Service. ## Who can use Memo You can use Memo if you are at least 16 years old and capable of forming a binding contract under the laws of your jurisdiction. If you're using Memo on behalf of an organization, you represent that you have authority to bind that organization to these Terms — and "you" in these Terms means both you and the organization. You are responsible for keeping your account credentials secure and for all activity that happens under your account. ## What Memo is Memo is a creative platform for capturing inspiration, organizing references, and generating images and videos with AI assistance. The Service includes: * The web application at memo.solutions and app.memo.solutions * The Memo — Inspiration Board Capture browser extension * Any APIs, documentation, and supporting services we publish We may add, change, or remove features over time. We try to give reasonable notice for material changes that affect paid features. ## Your content You keep ownership of the content you upload, save, or paste into Memo, and of the prompts you write ("Your Content"). You also keep ownership of the images, videos, and other outputs Memo's AI generates from your prompts ("Generated Content"), to the maximum extent ownership of AI outputs is recognised under applicable law. You grant Memo a worldwide, non-exclusive, royalty-free licence to host, store, transmit, process, and display Your Content and Generated Content solely as needed to operate the Service for you and your collaborators — including running it through third-party processors (Supabase, Vercel, model providers) on our behalf. This licence ends when you delete the content or your account, except where we are legally required to retain it. **Saved references.** Some features — the browser extension and connected AI agents — let you save copies of publicly available web content (images, video clips, page previews) into your workspace as creative references. You direct each save, and saved references are stored privately for you and your workspace collaborators; Memo does not publish them. Saving something into your library does not give you any rights in it: you are responsible for how you use saved references, including making sure any external or commercial use respects the rights of the original creator. If a rightsholder objects to content saved in a workspace, we handle it under **Copyright complaints** below. You are responsible for making sure you have the rights to upload and use Your Content, and for the choices you make about what to generate. You must not upload or generate content that: * Infringes someone else's copyright, trademark, or other intellectual property * Depicts a real person without their consent in a way that's defamatory, sexual, or misleading * Is illegal where you live or where the Service is operated * Violates the **Acceptable use** rules below ## Acceptable use You agree not to: * Use the Service to generate sexual content involving minors, content that promotes terrorism or mass violence, or other content prohibited by our model providers' policies * Attempt to bypass safety filters, rate limits, credit metering, or access controls * Reverse-engineer, decompile, or scrape the Service except as expressly permitted by law * Use the Service to build a competing AI image or video generation product * Resell, sublicence, or share workspace access in a way designed to circumvent seat or plan limits * Upload malware, run automated load against our infrastructure, or interfere with another customer's use of the Service We may suspend or terminate accounts that violate these rules. ## Generated content and AI limitations Memo uses third-party AI models for image and video generation, image analysis, and chat. These models can produce content that is inaccurate, offensive, biased, or that resembles existing works. You are responsible for reviewing Generated Content before publishing or using it externally. We do not guarantee that Generated Content is unique, free of similarity to other works, or suitable for any specific purpose. Run your own brand, legal, and IP checks before commercial use. ## Copyright complaints We respect the intellectual property of others and expect users of the Service to do the same. If you believe content stored on the Service infringes your copyright, send a notice to [support@memo.solutions](mailto:support@memo.solutions) with the subject line "Copyright complaint", or by mail to the address in **Contact** below, including: 1. Identification of the copyrighted work you claim is infringed 2. Identification of the material you claim is infringing, with enough information for us to locate it (for example, the URL of the item) 3. Your name, address, email, and telephone number 4. A statement that you have a good-faith belief that the use is not authorized by the copyright owner, its agent, or the law 5. A statement, made under penalty of perjury, that the information in your notice is accurate and that you are the copyright owner or authorized to act on the owner's behalf 6. Your physical or electronic signature On receiving a valid notice, we will remove or disable access to the identified material promptly and notify the user who stored it. That user may submit a counter-notice containing their contact details, identification of the removed material, and a statement under penalty of perjury that they believe the removal was a mistake or misidentification; if we receive a valid counter-notice, we may restore the material unless the complainant informs us within 14 business days that they have sought a court order. We terminate the accounts of repeat infringers in appropriate circumstances. ## Plans, credits, and billing Memo offers free and paid plans. Paid plans are billed through Stripe. * **Credits** — paid features (image and video generation, analysis, agent chat) are metered in credits. Each plan includes a monthly credit allocation; additional credits can be purchased as top-ups. * **Billing cycle** — subscriptions renew automatically at the end of each billing period until cancelled. * **Cancellation** — cancel your subscription at any time from Workspace Settings → Billing. Cancellation takes effect at the end of your current billing period; you keep access until then. * **Refunds** — credit purchases and subscription fees are non-refundable except where required by applicable consumer law. If you believe you were charged in error, email us at [billing@memo.solutions](mailto:billing@memo.solutions) and we'll investigate in good faith. * **Failed payments** — if a payment fails, we may suspend paid features until the balance is settled. We'll send notice before any suspension. * **Price changes** — we may change prices for new billing periods with at least 30 days' notice to your registered email address. Credits expire at the end of each billing period unless your plan says otherwise. Top-up credits roll over while your account is active. ## Workspaces and roles Memo is built around workspaces. The workspace **owner** controls billing and can invite, promote, demote, and remove members. Other roles (admin, editor, viewer) have progressively narrower permissions, described in [Members & Roles](/workspaces/members-and-roles). If you're an owner, you are the billing party for that workspace. If you delete a workspace, the data inside it (inspirations, generations, brand kits, projects, chat history) is permanently removed. ## Browser extension The Memo browser extension is provided under these Terms as part of the Service. Installing or using the extension constitutes acceptance. The extension only reads page content you explicitly capture; see the [Privacy Policy](/legal/privacy) for the full data practices. ## Changes to the Service We may update, modify, or discontinue features of the Service. For paid features that are materially changed or removed, we'll give reasonable notice and, where appropriate, prorated credit for the remainder of the affected billing period. ## Termination You can stop using Memo at any time, and request deletion of your account by emailing [support@memo.solutions](mailto:support@memo.solutions). We may suspend or terminate your access if: * You materially breach these Terms * We're required to do so by law * Continuing to provide the Service to you would expose Memo or another user to serious risk On termination, your right to use the Service ends immediately. We retain limited data as described in the [Privacy Policy](/legal/privacy) — usually deleting account-linked data within 30 days. ## Disclaimers The Service is provided "as is" and "as available", without warranties of any kind, express or implied. To the fullest extent permitted by law, Memo disclaims all warranties of merchantability, fitness for a particular purpose, non-infringement, and uninterrupted or error-free operation. We do not warrant that Generated Content is accurate, original, non-infringing, or suitable for your use case. We do not warrant that the Service will be available without interruption. ## Limitation of liability To the fullest extent permitted by law: * Memo's total liability for any claim arising out of or related to the Service is limited to the amount you paid us for the Service in the 12 months before the event giving rise to the claim, or USD 100, whichever is greater. * Memo is not liable for any indirect, incidental, consequential, special, or punitive damages, including lost profits, lost revenue, lost data, or business interruption — even if we've been advised of the possibility. Some jurisdictions don't allow these limitations; in those jurisdictions, the limitations apply to the maximum extent permitted. ## Indemnification You agree to defend, indemnify, and hold harmless Memo and its officers, employees, and agents from any third-party claim arising out of (a) your use of the Service in violation of these Terms, (b) Your Content or Generated Content you publish externally, or (c) your violation of any law or third-party right. ## Governing law and disputes These Terms are governed by the laws of the State of Delaware, United States, without regard to conflict of laws principles. Any dispute that cannot be resolved informally will be brought exclusively in the state or federal courts located in Delaware, and you consent to personal jurisdiction there. If you live in a jurisdiction that grants you mandatory consumer-protection rights, nothing in this section overrides those rights. ## Changes to these Terms We may update these Terms from time to time. Material changes will be communicated via email to your registered account, and a notice will appear in the app on your next sign-in. The "Last updated" date at the top of this page is always current. Continuing to use the Service after a change takes effect means you accept the updated Terms. ## Contact Questions, notices, or legal correspondence: * **Email**: [support@memo.solutions](mailto:support@memo.solutions) * **Address**: 251 Little Falls Drive, Wilmington, DE 19808, United States # Analyzing Images Source: https://docs.memo.solutions/save-organize/analyzing-images Extract the full creative DNA from any saved image — color palette, composition, lighting, style, mood — and turn it into reusable prompts and brand assets. Analysis turns a pretty picture into reusable creative DNA. Memo breaks down any saved inspiration into its visual components — the lighting setup, the color palette, the composition decisions — so you can understand why it works and apply those qualities to new work. ## What you get Run analysis on any inspiration (\~1 credit) and you get back: | Section | What's extracted | | --------------------- | ----------------------------------------------------- | | **Color palette** | 6 hex swatches, click to copy any | | **Generation prompt** | A copyable prompt that could recreate a similar image | | **Composition** | Layout, framing, perspective, focal point, depth | | **Style** | Medium, aesthetic, era, references | | **Lighting** | Type, direction, quality, shadows, highlights | | **Mood** | The overall feeling | | **Texture** | Surface qualities and materials | | **Elements** | Subjects, objects, text overlays | | **OCR text** | Any text detected in the image | ## Running analysis Open any inspiration and switch to the **Analyze** tab. If it hasn't been analyzed yet, click the analyze button. Results are saved permanently — you pay once, see the results forever. Click **Re-analyze** at any time for a fresh pass. ## Copy as prompt Each section has its own **Copy** button in the header. Click it to get a prompt-ready string for just that section — useful for grabbing the lighting setup without copying everything else. The full generation prompt has its own copy button too. Templates for each section: * **Composition** — `"{layout} layout, {framing} framing, {perspective} perspective, {depth}"` * **Style** — `"{medium}, {aesthetic} aesthetic, {era} era, inspired by {references}"` * **Lighting** — `"{type} lighting, {direction}, {quality} quality, {shadows} shadows"` * **Mood & Texture** — `"{mood} mood, {texture} texture"` * **Elements** — `"Subjects: {subjects}. Objects: {objects}. Text: {text}"` ## Save as Style Reference Click **Save as Style Reference** in the Analyze tab footer (or from the action bar below the panel). This does three things: 1. Auto-triggers analysis if none exists yet 2. Creates a **brand asset** from the inspiration plus its analysis data 3. Saves the extracted color palette to your workspace's brand colors The inspiration becomes a first-class reference — available for @mention in Studio, carrying its full analysis as creative context. ## Using analysis in Studio When you reference an analyzed image in Studio, the agent gets access to all of this data — not just the pixels. It can match the lighting setup, use the color palette as a constraint, or apply the composition style to a new subject. This is where the system compounds. Save → analyze → reference → generate. Each step builds on the last. # Collections Source: https://docs.memo.solutions/save-organize/collections Organize inspirations, generated references, and assets in general or Brand Kit collections. Collections are lightweight folders for grouping related references. Membership is explicit: adding an item to a collection links it there, so one item can live in several collections without being duplicated, and retagging an item later never changes which collections it belongs to. ## Browsing collections In **Collections**, the newest created collections appear first. The grid uses the same landscape cards as Studio projects and adds columns on wider screens. Use the **List / Grid** switch at the top right to choose between previews and compact rows with inspiration counts and creation dates. Memo remembers this choice in your browser. Search filters collection names in either layout. Select anywhere on a card to open its collection. The inspiration count sits directly beneath the title. ## Creating a collection Create a collection from your library (**Collections** view → **New collection**). Give it a name, then pick what goes in: saved inspirations from the **All** tab, or Studio generations from the **Generated** tab of the same picker. Choose **Add to collection** on an inspiration, generated result, or asset card to open the same navigator: 1. Choose **General collections**, or select a **Brand Kit** on the left. 2. Check the collections you want on the right. Each checkbox saves immediately; an existing membership is already checked. 3. Switch destinations to file the same item in more than one place. 4. Choose **Done** when finished. **New collection** creates a collection in the destination you are viewing and adds the item to it. If saving fails, the checkbox returns to its previous state and a message explains the error. Uncheck a collection to remove that membership without deleting the item. Reopening the picker reuses recently loaded collections and their checkmarks. Memo prepares destinations as you open an item's menu or point to a destination. A destination you have not loaded yet may briefly show a loading indicator. After a save is confirmed, you can continue immediately while the library refreshes in the background. ## Taste profile and keywords Open a collection and the header above the grid tells you, and your AI, what the references have in common: * **Taste profile** — a short paragraph describing the aesthetic that ties the references together: medium, mood, palette and lighting, subjects, era or influences. Memo writes it the first time you open a collection that has references, from the titles, descriptions and tags it already produced for each one. No credits are charged. * **Keywords** — five to eight prompt-ready phrases distilled from the same references. Use the copy icon next to the heading to paste them straight into a prompt. The profile remembers how many references it was written from. Add or remove references and the header notes that the collection has changed; use the refresh icon next to **Taste profile** to write it again. A collection with no references shows an **Analyze collection** prompt once you add some. Viewers see the header but cannot refresh it. Your connected agent gets the same header: `get_collection` returns the taste profile and its keywords, and flags a stale profile. Ask it *"what's the vibe of the Futurist Glam collection?"* and it answers from the profile; ask it to generate from the collection and the profile is its brief. The agent can also write or refresh the profile itself with `update_collection`, after reading the references, so a collection filled by your agent is described by your agent. ## Adding and removing items * **Add to collection** — from the card’s menu; the navigator shows both General collections and Brand Kits * **Add inspirations** — inside a collection, the picker at the top right adds saved inspirations or generated results * **Remove from collection** — same menu when browsing within a collection Your connected agent can also file in bulk by tag (`add_to_collection` with `tags`): every inspiration carrying any of the chosen tags is added once, as a snapshot rather than a live rule. Adding an item to a collection doesn't move it out of your main library. Removing it doesn't delete it — it just unlinks. ## Filing generations Anything you generate can become a curated reference, from wherever you are looking at it: * **Studio → a project's assets** — hover a card and choose **Add to collection**, or open the card and use the action bar * **Workflows → Runs** — the same action on every run output * **Images** and **Videos** tools — hover a result tile The picker is the one inspiration cards use, and it already knows which collections the generation is in. Under the hood Memo copies the media into your library, so the reference keeps working even if the project it was made in is deleted later. Each generation maps to one library item: adding it to a second collection files that same item, never a duplicate. Filed generations live inside collections only, so the main **Inspirations** feed stays what you captured from the web. Your connected agent has the same door: `add_inspirations` with a `generation_id` and a `collection_id`. ## When to use collections Use collections to group references for a purpose: * "Q3 campaign moodboard" * "Brand refresh 2026" * "Client X — winter shoot" * Style exploration — group by aesthetic direction to compare approaches A collection groups references; a Studio project holds the working canvas, its conversations and its own assets page with the folders you create. Project folders sort what was made in one project; collections gather references across projects. Neither determines brand inheritance. General and Brand Kit collections have separate homes, but share the same filing navigator. An item can belong to both. For assets that belong to a brand, use **Assets → Add to collection** and choose the Brand Kit on the left. Kit collections support product and style images, characters, graphic elements, photography, and videos. A kit’s **Unfiled** view keeps assets accessible after their last kit collection membership is removed. See [Filing assets into a kit](/brand-kits/setting-up-your-brand#filing-assets-into-a-kit). Your connected agent can read a collection with `get_collection`, including its captured and generated references. Ask it to use that named collection when preparing a brief; collection membership alone does not attach every item to every scene. ## Managing collections From your library you can: * **Browse** within any collection to see its contents * **Rename** a collection * **Delete** a collection (removes the grouping, not the items inside) Embedded videos such as YouTube references can be filed in General collections. Upload the actual clip to save it in a Brand Kit. Filing an existing asset preserves its original type and name; no extra media upload is needed. # Library Source: https://docs.memo.solutions/save-organize/library Browse, search, and filter your saved inspirations and generated images — one masonry grid that holds everything. The library is your visual home base. A masonry grid of everything you've saved and everything you've generated, filterable and searchable across your entire workspace. ## A living grid Cards keep their natural shape — nothing is cropped to a uniform square — and saved video clips **play silently in the grid** as they scroll into view. Playback is polite by design: clips only play while visible, a handful at a time, and heavier clips wait for a click on their play button instead of autoplaying (they show their length in a small pill). If your system is set to reduce motion, nothing autoplays. Click a video card to open it full-size with sound and controls. YouTube and Vimeo saves play their official player inside the detail view. ## Views The library has two views (top-right of the dashboard): * **Inspirations** — images and clips saved from the web or uploaded * **Collections** — curated groups of inspirations and filed generations Generated images and videos live in **Studio → Generations**, one card per project. Your Studio projects and your Assets (brand kits, assets, and skills) are separate destinations, reachable from the sidebar rather than being library tabs. ## Search The search bar searches your **entire library** — not just the cards visible on screen. It hits the server, so results are accurate across your whole workspace regardless of how far you've scrolled. Results update as you type with a brief debounce. The same server-side search works in **Studio → Generations** — find any generation by its prompt text, even if you haven't scrolled to it. ## Filters The filter menu narrows the grid by: * **Media type** — static, motion graphic, or video * **Tag** — any tag in your workspace * **Contributor** — who on your team saved it Filters combine with search. You can search "sunset" *and* filter by tag "warm tones" *and* narrow to a specific contributor — the results match all of them at once. Everything runs server-side, fast and accurate at any scale. ## Loading and pagination The grid loads lazily — first batch appears almost instantly, more loads automatically as you scroll. No "load more" button, no waiting for thousands of cards to download. While loading, **skeleton cards** (shimmer placeholders matching the card shape) hold the layout so nothing jumps when content arrives. When you've reached the end: "You've seen all your inspirations." ## Empty states Brand new library? The empty state explains the two ways to start filling **Inspirations**: save from the browser extension, or ask your connected agent to file references for you. Capture deliberately stays where you browse, so there is no duplicate in-app upload button. An empty **Studio → Generations** points you to your first project, where your first generated image or video will appear automatically. Each surface uses its own animated line illustration, but the placement, copy, and next action stay consistent across Memo. ## Context menu Right-click any card for quick actions: * **Add Tags** — tag without opening the detail modal * **Add to collection** — file into one or more collections * **Save as Style Reference** — creates a brand asset, auto-analyzes if needed * **Send to Studio** — creates a new project pre-loaded with this inspiration * **Delete** — removes the card (editors and admins only) ## Tags Tags are lightweight, freeform labels you attach to inspirations. They power the **Tag** filter and also drive [Collections](/save-organize/collections) under the hood. * **Add tags** — right-click a card → **Add Tags**. The tag picker shows every tag already in your workspace; type to filter. * **Create a new tag** — type the name and press Enter in the tag picker. New tags are normalized to lowercase and immediately available everywhere else in the workspace. * **Remove a tag** — click the × on its chip in the tag picker. * **Workspace-wide pool** — every tag any teammate creates becomes available to everyone in the workspace, so the vocabulary stays consistent. Tags are workspace-scoped, not personal. Pick names everyone on the team will use the same way. ## Generations **Studio → Generations** shows one card per project (plus **Unassigned** for anything left behind by a deleted project). Drill in for that project's grid. Cards show a **status badge** — color-coded for pending, generating, completed, or failed — and, on hover, four actions: * **Add to collection** — file the image or video into a collection as a durable reference (see [Collections](/save-organize/collections)) * **Save as reference** — copy an image into Assets → Images, or into a Brand Kit * **Download** — the full-resolution original when there is one * **Delete** The grid has its own infinite scroll pagination. ## What happens when something goes wrong Every save, delete, or edit shows a **toast notification** on failure — no silent errors. Permission denials get an explicit message ("You don't have permission to do this"). Destructive buttons disable while their action is in flight, so a frustrated double-click can't fire twice. ## Offline If you lose internet, an amber banner appears at the top of every page. When you reconnect, a brief green confirmation flashes and disappears. # Saving from the Web Source: https://docs.memo.solutions/save-organize/saving-from-the-web Capture anything visual from the web — through the browser extension or your connected agent — into one searchable library that grows with you. Saving an inspiration adds the actual media — an image or a video clip, along with its source link, title, and metadata — to your Memo library. Every inspiration shows up instantly in your dashboard and stays there, ready to be tagged, organized, [analyzed](/save-organize/analyzing-images), or sent into [Studio](/studio/overview). The philosophy: **save first, organize later.** Friction at save time means a smaller library. Capture liberally, sort in batches. Memo captures the real thing, not a bookmark: images are fetched at the best resolution the page offers, and motion pieces are saved as playable clips that loop right in your grid. ## From the web (browser extension) 1. Install the Memo browser extension 2. Sign in once 3. On any webpage, click the **Memo** button in your browser toolbar 4. Memo grabs the image — along with the title, source URL, and creator info when available 5. The inspiration appears immediately in your dashboard **Right-click an image** to save that specific image instead of the page's default. The extension auto-detects the source platform — Instagram, X, LinkedIn, TikTok, YouTube — and tags it with a small badge on the card. If your connection drops mid-save, nothing is lost: the extension keeps the save and retries in the background, and the toolbar badge shows how many are still waiting. Rejected files (too large, wrong type, over your plan's limit) are reported immediately instead of retried. ### Saving motion When the post you're hovering contains a video, the save panel shows an **Include clip** toggle (on by default, with the clip's length). Memo downloads the actual video file, stores it, and the card plays it in your grid. Videos on X and Pinterest video pins are captured natively — even though both players stream, Memo resolves the post to its real video file, so the save gives you the playing clip, not a screenshot of it. Some platforms stream video in a way that can't be downloaded. When that happens, Memo saves the frame you were looking at instead and tells you honestly — "clip saved as a frame" — so you always know whether you have the motion or a still. ## Through your connected agent There is deliberately no add button inside the app — your library fills from where you actually browse and work: the extension, and your AI agent. An agent connected through the [Memo connector](/get-started/connect-your-agent) can save **any URL** for you — just paste a link into your conversation and ask it to file the inspiration: * **A post or article** — the agent saves it with its preview image, title, and description * **An X post link** — the post's video (or full-size photo) is captured natively, with the post text as the card's title * **A Pinterest pin link** — a video pin's clip is captured natively; image pins are fetched at their original resolution * **A direct image or video file** — downloaded and stored in your library (videos up to 50MB, playable right in the grid) * **A YouTube or Vimeo link** — saved with its thumbnail; the video plays inside the detail view * **Files from your conversation** — agents can upload images they're working with and file them into collections Everything an agent saves is re-hosted into Memo's own storage, so cards never break when the original source takes the file down. ## What happens after you save The card appears instantly. In the background, Memo: * Runs the image through vision analysis and replaces the title and description with a clean, descriptive 5–8 word title and a 1–2 sentence summary * Detects the social platform if applicable and shows a badge * Records who saved it and when * Stores the source URL so you can always get back to the original You'll see a brief shimmer placeholder for a second or two while enrichment runs, then the real content fills in. If enrichment fails, the original scraped title stays. ## The detail modal Click any card to open a full-screen view — image on the left, detail panel on the right. ### Title and description The top of the panel shows the enriched title and description. Both are **click-to-edit** for editors and admins — click, type, press Enter or click outside to save. Press Escape to cancel. ### Details tab * **Source** — a clickable card back to the original. Where the platform makes it public, Memo shows the account that posted it: name and @handle for X, TikTok, YouTube, and Vimeo, with the real profile picture for X. Everywhere else it shows the platform's logo (or the site's favicon). * **Added by** — contributor avatar, with a "Claim" button if the inspiration was saved without a creator Tags are no longer part of this panel — AI enrichment makes every save searchable by content automatically, and [collections](/save-organize/collections) are the way to group the ones you want to keep together. ### Analyze tab Switch here to run deep analysis (\~1 credit). Full breakdown in [Analyzing Images](/save-organize/analyzing-images). ### Action buttons Below the panel: * **Open source link** — new tab to the original * **Send to Studio** — creates a new Studio project pre-loaded with this inspiration * **Save as Style Reference** — creates a brand asset from the inspiration, auto-triggers analysis if missing, saves extracted colors to your Brand Kit * **Delete** — removes the inspiration (editors and admins only) The top bar has a **Download** button that actually downloads the file — Memo handles the cross-origin blob fetch so you get the file, not a new browser tab. ## Deduplication Memo deduplicates by source URL. Saving the same page twice updates the existing record instead of creating a duplicate. ## Tips * **Install the extension on day one.** The value compounds as your library grows. * **Don't organize as you save.** Tags and collections can be added in batch later. * **Save your own work too.** The system treats uploads and web saves identically. ## Troubleshooting **The extension button is greyed out.** You're probably signed out. Click the extension icon and sign back in. **My inspiration shows a broken image.** The source page may have removed the image, or it's behind authentication. Try saving again from a fresh page load. **I don't see what I just saved.** Refresh the dashboard. If it still doesn't appear, check your filters — a tag or contributor filter may be hiding it, or the search box may be narrowing the view. # Brainstorm Mode Source: https://docs.memo.solutions/studio/brainstorm-mode A conversational Studio mode that explores concepts without generating anything. Think before you make — the agent stays in ideas and research until you're ready to create. Brainstorm is the mode you switch to when you want to **think with the agent** before you start generating. Every normal conversation in Studio is in Create mode — the agent will happily fire off images as soon as it understands what you want. In Brainstorm mode, it doesn't have that option. Brainstorm is the working session that comes *before* the creative brief. No commitments, no credit spend on generation, no cluttered canvas. Just you and the agent, shaping the idea until it's ready to execute. ## When to use it * **The idea is still fuzzy.** You have a vibe but not a brief. Let the agent help you name it. * **Before a big campaign.** Work out audience, tone, platform strategy, visual direction — then flip to Create and the agent already knows what it's building. * **Exploring a brand's voice with a new product.** Discuss positioning, visual anchors, and creative direction without producing anything. * **You want the agent to research first.** Brainstorm keeps the conversation in concept-mode while still letting the agent search your inspirations and brand assets. If you already know what you want to make, skip Brainstorm and go straight to Create. Brainstorm is for moments where the thinking is the work. ## How to switch modes The mode toggle lives in the Studio chat composer, next to the model selector. Two choices: * **Create** (default) — the agent can generate images and videos, present briefs, run skills, and do anything else in Studio * **Brainstorm** — the agent can't generate. Everything else still works: searching brand assets, searching inspirations, asking you clarifying questions, exploring ideas You can flip between them at any point in the same conversation. The agent carries context forward — anything you brainstormed shows up when you switch to Create. ## What the agent does in Brainstorm * **Asks you questions** — presented as clickable option cards rather than text lists, so you step through choices fast * **Searches your library** — if you're brainstorming a campaign, it can surface relevant inspirations and brand assets from what you've already saved * **Discusses creative direction** — tone, mood, audience, platform strategy, visual anchors * **Helps you draft a brief verbally** — working toward what you'll confirm once you switch to Create What it won't do: * **Generate images or videos** — the `generate_image` and `generate_video` tools aren't available in Brainstorm * **Present a creative brief card** — briefs are a Create-mode artifact. Brainstorm keeps it conversational ## Switching to Create with context When you're ready to make the work, flip the toggle to Create. The agent reads back through your brainstorming conversation and **skips questions that were already answered**. If you discussed aspect ratio, audience, and visual direction in Brainstorm, it won't re-ask those things — it goes straight to presenting a brief or generating. This is the payoff: all that thinking you did in Brainstorm becomes the agent's starting context in Create. ## Cost Brainstorm still uses the agent (so each turn consumes a small amount of credits for the chat itself), but you're not generating images or videos — the expensive operations are disabled. It's dramatically cheaper than a Create-mode session. ## Tips * **Start broad, narrow fast.** Use the first few turns to stake out the problem space, then let the agent's questions focus you. * **Name your constraints.** "We can't use stock photography" or "the product can't be the hero in every shot" — tell the agent early and the brainstorming converges faster. * **Switch to Create when you can describe the outcome in a sentence.** If you can't, you're not done brainstorming. * **Brainstorm works inside a project.** The context stays with that Studio project's chat history, so you can come back to it later. # Creating Images Source: https://docs.memo.solutions/studio/creating-images How to generate images in Studio — prompting, references, brand assets, iteration, and the cinema preset system. ## Prompting Describe what you want in natural language. The agent interprets, refines, and generates. Good prompts tend to include: * **Subject** — what's in the image * **Style** — photography, illustration, 3D render, editorial * **Mood** — minimal, dramatic, warm, cinematic * **Technical** — lighting direction, camera angle, color palette, lens You don't need to be an expert prompter. The agent asks clarifying questions when a prompt is vague. It also has access to a deep prompting framework that covers text-to-image, multimodal editing, style transfer, and text rendering. By default, Memo enhances your prompt before generation (**Memo Magic**). You can also switch to **Simple** mode to send your exact words verbatim — useful when you've written a precise prompt yourself. See [Simple vs Memo Magic](/studio/prompt-modes) for the full breakdown. For a prompt-first workflow, open **Image** or **Video** from the sidebar. On a new workspace, the first-run screen leads straight into the composer; describe the result, choose the model and settings, and press Enter. Your completed generations collect on the same page and in Studio → Generations. ## Using references Drag any inspiration from your library onto the Studio canvas. When you mention it in chat, the agent uses it as visual context — matching its style, composition, or color palette. If the inspiration has been [analyzed](/save-organize/analyzing-images), the agent gets the full creative breakdown — not just the pixels. It can match the lighting setup, use the extracted palette, or apply the composition style to a new subject. ## Brand assets as constraints Type `@` to mention a brand kit or specific asset. The agent loads your brand context and generates within those constraints. This is how you get consistency without repeating yourself every prompt. See [Using Brand Assets in Studio](/brand-kits/using-brand-assets) for the full workflow. ## Aspect ratio and quality The agent supports multiple aspect ratios (square, landscape, portrait, 16:9, 9:16) and quality levels: * **1K** — fast drafts * **2K** — high quality (default) * **4K** — highest quality You can specify these in your prompt, or the agent will choose smart defaults based on your use case. ## Working with a result Click a finished image or video on the canvas and a small toolbar floats above it with the actions you reach for most: * **Edit prompt** — opens the result in the editor, with the original shown beside the prompt for comparison: rewrite the prompt, manage references in the **References** card (the dashed **+** tile opens the picker), change the model, aspect ratio, quality or duration in **Output**, then press **Regenerate** (the credit cost is on the button). The new version lands as its own node next to the original, which stays untouched * **Reframe** (images) — re-generate the same picture at another aspect ratio and quality * **Status** — mark the result *Needs Review*, *In Progress*, *Approved*, *Rejected* or *Pending*; the status shows next to the node's name and is saved with the project * **Duplicate** and **Delete** Right-click for the longer list (Cinema Presets, Extract Grid, Convert to SVG, Save to Brand Assets, Download). Double-click a result, or press its **Expand** button, to open the full preview: the complete prompt, the model, duration, aspect ratio and quality it was generated with, its source images, and the same status picker. ## Cinema presets Cinema presets turn one image into a full nine-shot coverage plan — camera coverage, closeups, cutaways, or story beats, organized by category. Right-click any image on the canvas, pick **Cinema Presets**, browse or search the tree, click a preset, then choose how many shots to run (3, 6, or 9 — each shot bills as its own image) and a quality (1K / 2K / 4K). Each preset generates **separate high-fidelity images** — one per shot, grouped together on the canvas — rather than a single collage, so no shot loses detail. Every shot is its own full-resolution image you can reframe, save, or turn into video individually. Behind the scenes: * Memo analyzes your image's subject and rewrites each shot description around it * Each shot generates independently on a high-fidelity model, using your image as the visual reference * Running fewer than nine samples evenly across the plan, so 3 shots still span it from wide to detail * Shots land as a named group arranged three per row, matching the preset's plan Presets give you consistent starting points while leaving room for creative direction. ## Extract Grid Right-click any reference image on the canvas and pick **Extract Grid** to reuse its layout as a template. Memo analyses the source — composition, panel structure, alignment — and turns it into a reusable grid you can populate with new content. Useful when you've found a layout you like and want to keep its bones while changing everything inside it. ## Iteration After a generation, you can: * Ask for **variations** — "try a warmer color palette" * Request **edits** — "remove the text overlay" * **Start fresh** — "let's try a completely different direction" Each iteration appears as a new node on the canvas. You never lose previous versions. The full conversation history is preserved, so the agent remembers the creative thread across every turn. ## Generations run in the background Generations are queued. The moment you submit, the request is accepted and the canvas shows a placeholder node. You can keep prompting, switch projects, or close the tab — when you come back, completed generations are already there. There's nothing you have to wait around for. ## Uploading your own references Drag any image from your desktop onto the canvas, or press **Cmd+U** to open the upload dialog. Uploads are capped at **30 MB per file** — high enough for full-quality stills, RAW exports, or short animation frames. ## Design Editor Click into any image node and select **Edit** to open the Design Editor — a lightweight overlay tool for adding text, simple shapes, and brand-locked color fills directly on top of an image. When you're ready to publish, click **Export** for one-click platform sizing: * **Instagram Post** — 1080×1080 * **Instagram Story** — 1080×1920 * **X / Twitter Post** — 1200×675 * **LinkedIn Post** — 1200×627 * **TikTok Cover** — 1080×1920 * **Original** — keeps the source resolution You can either download the export locally, or save it back as a new node on the canvas to keep iterating. ## Video generation The agent can also generate videos with control over: * **Duration** — from 2s up to 30s in a single pass, depending on the model * **Resolution** — 480p up to 4K on models that support it * **Aspect ratio** — 16:9, 9:16, 1:1, and more on select models * **References** — a start frame, an end frame, and reference images, where the model supports them; the composer shows a slot for each input the selected model accepts * **Creative direction** — describe motion, camera movement, and action Videos appear as playable nodes on the canvas with the same status badges and action buttons as images. ## Naming and finding generations Every generation gets a title automatically, but the ones you'll reuse deserve real names. Open any generation and use the **Name** card in its detail panel to rename it — names are what the search bar matches, so a keeper named `product-fw25-sneaker-red-v2` is findable next week, next month, by anyone on the team. The same names work for agents: a connected agent can name outputs at generation time and re-find them by name later, so a library your team names by hand and a library your agent builds stay one library. Two habits keep it clean: name outputs the moment they're approved (drafts can keep their automatic titles), and never reuse a name — a new version gets a new suffix. ## Error handling The system classifies errors into specific categories — timeout, prompt too long, safety filter, rate limit, asset upload failure, upstream outage — and shows a clear message for each. Failed generations stay visible on the canvas at their saved position with the error displayed. If the canvas autosave fails three times in a row, a persistent banner appears. It auto-clears when the next save succeeds. # Creative Briefs Source: https://docs.memo.solutions/studio/creative-briefs Prepare multiple image and video scenes in one brief, then generate from the connected canvas nodes. A **Creative Brief** brings a campaign's scenes together. Use it to write prompts, select references and choose output settings. Press **Generate** on the brief card and every scene becomes its own node next to the brief, named after the scene, and runs. ## Prepare your scenes 1. Describe the campaign in Studio chat. Mention the brand kit and references you want to use. 2. Open the brief from its canvas card or the **Open brief** link in chat. 3. Choose a scene in the left list. Edit its prompt in the center and its output settings on the right. 4. Add, reorder or remove scenes using the scene list, and rename the open scene from its title above the prompt. A brief can contain both images and videos. 5. Choose **Back to canvas**, then **Generate** on the connected image or video generator. If a connected generator was deleted, opening the brief creates the missing connection again. Reopening an already connected brief does not create another generator. ## Write and refine prompts Click anywhere in the prompt to edit. Repeated spaces, ordinary keyboard navigation, selection and undo work inside the editor. Changes are saved as you write, including the latest text when you switch scenes or close the brief. Write creative instructions such as “warm lighting” or “negative space” directly in your prompt. The brief has no separate Styles library or automatic attribute popovers. Older saved style selections are preserved as visible prompt text when the brief opens. ## Choose scene references Use **+** below the prompt to open the reference picker, or type `@` to choose an available reference. Each scene's thumbnail strip shows the references used for that scene. An inline reference is one locked chip. Its label cannot be edited inside the prompt. Use the asset's own editor to rename the asset. * Remove a chip with its X or by selecting it and pressing Backspace or Delete. * If the same reference is mentioned twice, deleting one mention keeps the other. * Deleting its final mention detaches it from that scene. * Removing a thumbnail below the prompt also removes all its inline mentions in that scene. * Other scenes keep their own selected references. Removing a scene reference does not delete the original asset from its brand kit. A color such as **Stripe Purple (#533AFD)** displays a small swatch. The exact color text remains in the prompt. Swatches do not become additional reference images. ### Reference purposes Each thumbnail has a purpose menu below it. Image scenes can mark a reference as **Character**, **Location**, **Prop or product**, **Pose or staging** or **Style**. The purpose is described to the model together with the image. Video scenes can also mark a reference as the **Start frame** or **End frame**; a scene has one of each. A saved purpose stays with the reference when you reorder thumbnails. A video scene with no purposes uses its first reference as the start frame, and the strip labels that thumbnail **Start · auto**. ### References not used in any scene When you pick references in chat and the agent does not assign them to a scene, the brief lists them under **Not used in any scene** instead of adding them to every scene. Select one to add it to the current scene, or choose **Add all to every scene**. The brief card on the canvas shows how many references are still unassigned. ### From a connected agent A connected agent (see [Connect your agent](/get-started/connect-your-agent)) can create a brief for a multi-scene ask, read the brief you have open, and edit scenes, references and purposes for you. Changes made while the project is open appear in the editor immediately and can be undone like your own edits. Generation still runs from the connected canvas generators, after you approve the estimate. ## Output settings The **Output** card beside the prompt shows the scene's model, aspect ratio and quality, and its estimated credits. Quality lists the selected model's real tiers (1K, 2K, 4K for images; 480p, 720p, 1080p and similar for video), and the estimate follows it. Video scenes add duration and audio controls. Available options depend on the selected model. Each scene's estimate also appears beside it in the Scenes list. Scene settings are what each scene node runs with. A scene that leaves a setting empty follows its node's default, and the agent is told which fields defaulted. A shared character reference does not by itself make one scene depend on the previous scene's output. ## Generate from the brief card **Generate** on the brief card lays every scene out as its own card to the right of the brief and runs them all at once. All of the brief's cards sit in one group named after the brief. Each card is named after its scene, shows the scene text with an **Edit in brief** link and one line of settings, and carries its own copy of the prompt and settings, so it stands on its own. No wires are drawn between the brief and its cards. Every output is named after its scene, so it is easy to find again in the library and to reuse as a reference. Scenes that already have a card keep it; pressing Generate again re-runs every scene in place and only adds cards for new scenes, inside the same group. Credit limits and errors show on the card that hit them. The canvas displays generation progress, outputs and errors. A failed generation leaves the brief available for correction. Check the affected generator's results before starting another run; generating a whole brief again can generate successful scenes again too. Credit limits and workspace permissions still apply. ## Older saved briefs Older chat brief cards now open the same expanded brief. If an older brief contains one document instead of structured scenes, Memo shows **Your saved brief**. Choose **Create image scene** or **Create video scene** to bring that document into one editable scene. Review it and add further scenes as needed. The import preserves the original document under **Original saved brief**. It does not use AI to reinterpret your saved work or start a generation. ## Context efficiency On brief-answer turns, Memo keeps the kit's asset names and IDs, colors, fonts and rules available without repeatedly sending its images to the chat model. Recent brief details and your latest answer remain in context, including supported corrections from longer conversations. The brief editor groups continuous typing into useful canvas undo steps without postponing the saved text. These changes reduce unnecessary editing work; actual generation costs still depend on the chosen models and outputs. # Keyboard Shortcuts Source: https://docs.memo.solutions/studio/keyboard-shortcuts Every keyboard shortcut in Studio — canvas tools, navigation, generation, and chat. Studio is built for keyboard-first work. Every shortcut here uses **Cmd** on Mac and **Ctrl** on Windows / Linux. ## Tools | Shortcut | Action | | -------------- | ------------------------------------------ | | `V` | Switch to the **select** tool | | `H` | Switch to the **pan** tool | | `Space` + drag | Pan the canvas without leaving select mode | | `Cmd+U` | Open the upload dialog | ## Selection and editing | Shortcut | Action | | ---------------------- | ----------------------------------------------- | | Click | Select a node | | Shift + click | Add or remove a node from the current selection | | Drag-select | Marquee-select multiple nodes | | `Backspace` / `Delete` | Delete the selected node(s) | | `Cmd+G` | Group selected nodes | | `Cmd+Z` | Undo (50-step history) | | `Cmd+Shift+Z` | Redo | ## Chat and mentions | Shortcut | Action | | ------------- | -------------------------------------------------------------------------------- | | `@` | Open the mention picker (brand kits, assets, colors, instructions, canvas nodes) | | `Enter` | Send the current chat message | | `Shift+Enter` | New line in the chat input | | `Escape` | Close the active modal or popup | ## Browser extension The keyboard shortcut for capturing from the web lives outside Studio: | Shortcut | Action | | -------------------------------- | ----------------------------------------------- | | `Cmd+Shift+M` (Mac) | Open the Memo capture popup on the current page | | `Ctrl+Shift+M` (Windows / Linux) | Same | The extension shortcut is reassignable from `chrome://extensions/shortcuts`. ## Tips * **`H` is for "hand"** — same convention as Photoshop, Figma, and Illustrator. `V` is select. * **Hold space** when you want to pan briefly without losing your select tool. Release to go straight back to selecting. * **Undo runs 50 deep**. You can iterate aggressively without fear of losing earlier work. # Studio Overview Source: https://docs.memo.solutions/studio/overview An infinite canvas paired with a creative agent that knows your brand. Describe what you want, provide references, and the system generates — all in one conversation. Studio is where the work gets made. An infinite canvas paired with a conversational agent that carries your brand context, sees your references, and generates images and videos directly onto the canvas. One idea becomes every format and three variants. The system coordinates. You stay the taste-maker. ## The canvas An infinite canvas where every generation, reference, and asset lives as a moveable node. **Generator nodes** do the work: * **Image Generator** — prompt, model picker, references, and a Generate button in one node; outputs land beside it and can chain into further edits * **Video Generator** — model-aware video generation with per-model durations and resolutions * **Director** — compose an idea plus style choices into a polished prompt, then hand it to a generator * **Workflow** — a saved multi-scene recipe placed on the canvas, ready to run * **Assistant** — chat with the Studio agent right on the canvas **Content and reference nodes** feed them: * **Image / Video** — generated results with status, playback, and action buttons * **Upload** — images you've dragged in as references * **Asset reference** — brand assets pulled from your Brand Kit * **Color** — a brand color as a first-class reference * **Text** — editable notes; a **List** node fans a set of text items out into prompt variations * **Description** — prompt descriptions attached to generations * **Brief** — structured creative briefs with per-deliverable settings * **Group** — combine nodes into a named, color-tinted frame (Cmd+G to group, Cmd+Shift+G to ungroup). Click the title to rename it. Selecting a frame shows its toolbar: pick a color, ungroup, arrange members (grid, horizontal, vertical, moodboard, or workflow order — the frame tightens around the result), duplicate the whole frame (Cmd+D), delete it with its members, download every image as a zip, or set a review status. Dragging a member around inside the frame keeps it in the group; dragging it out removes it You can arrange, compare variations, build sequences, or lay out a full campaign — all on one canvas. **Keyboard shortcuts:** * **V** — switch to the select tool * **H** — switch to the pan tool * **Space + drag** — pan the canvas without leaving select mode * **Cmd+U** — upload media to the canvas * **Cmd+G** — group selected nodes * **Cmd+Z / Cmd+Shift+Z** — undo/redo (50-step history) * **Backspace / Delete** — delete selected nodes A full list lives in [Keyboard Shortcuts](/studio/keyboard-shortcuts). ## The chat agent The right panel is your creative director. It's a conversational agent that can: * **Generate images** from your text descriptions * **Generate videos** with duration, camera, and motion control * **Search your inspirations** and brand assets for relevant references * **Present creative briefs** for multi-deliverable campaigns — whether parallel (independent images) or sequential (a storyboard that chains each scene onto the previous one). See [Creative Briefs](/studio/creative-briefs) for the sequential toggle * **Save work as brand assets** — feed generation results back into your Brand Kit The agent carries context across the full conversation. Ask for changes, variations, or new directions — it remembers what you've discussed and what you've generated. ### @mentioning brand assets Type `@` in the chat to mention a brand kit or specific asset. The agent loads your colors, typography, guidelines, and reference images as creative constraints. Mentions appear as styled chips with thumbnails in your message. ### Streaming Responses stream in real-time with thinking indicators, per-tool status messages ("Composing the scene..."), and generation status updates. A heartbeat keeps the connection alive during long operations. ## Projects Each Studio canvas is a **project** — its own canvas, its own chat history, its own references. Projects save automatically (2-second debounce on every change, plus a save on unmount). If your workspace has no Studio projects yet, Studio opens on a focused first-run state with an animated canvas illustration and a **New Project** action. Search appears after the first project exists, when it has something to act on. From the Studio tab on your dashboard you can: * **Create** new projects * **Open a project's assets** (card menu → **Project assets**) — everything generated in it, filed into folders * **Rename** projects (card menu, or click the title in the canvas header) * **Search** across all your projects * **Delete** projects (cascades through all generations, chat messages, and stored images) Use the **List / Grid** switch beside Studio search to choose landscape previews or compact rows. Each row shows the project name and last-edited date, with the same **Project assets**, **Rename**, and **Delete** menu actions available for your role. Memo remembers Studio’s layout independently of other libraries. Search works in both views. Project cards use the same shape as Collections and the Workflows library: a preview of the project's latest generations (up to four, as a mosaic) with the last-edited date directly below its title. Select anywhere on the card to open the project. Projects are paginated for large collections. ### Project assets Use **List / Grid** beside search to choose your layout. List uses the same rows as Collections and Brand Kits: open a folder to browse its files, or open a file to preview it. Thumbnails, supporting text and dates stay consistent, with **Move to folder** and **Download** beside each file. The layout remains selected as you enter folders, return to the project’s assets and reload the page. Every project has an assets page — the folder icon in the canvas header, or **Project assets** in the card menu. It works like a drive: * **Folders.** A project starts with no folders. Add your own with **New folder** (for example "Characters" or "Scene 3 — Kitchen"); rename or delete them from the folder's menu. A folder can only be deleted once it is empty, so files are never lost with it. A project holds up to 100 folders; past that, Memo asks you to reuse or tidy one before adding another. * **Files.** Everything you generate in the project lands here, unfiled, the moment it completes. Hover a file and choose **Move to folder** (also in the expanded view) to file it; a file lives in one folder at a time. The **Unfiled** section only shows while something is in it; once every file has a folder, the page is just your folders. Search looks across every folder in the project. * **Moving between projects.** Files moved to another project appear in **Unfiled** unless you choose a folder in the destination. Moving within the same project keeps their folder. Files carrying an old folder that no longer exists also appear in **Unfiled**. * **Edits survive background work.** Filing or approving a file while Memo finishes saving or describing it keeps those changes. An automatic title fills an empty name; it does not replace a name you have already entered. * **Views.** Switch between the grid and a list with the toggle next to the search box. * **From the canvas.** Select a group frame and choose **File into folder** from its menu: a folder named after the group appears in the project's assets with the group's images inside (an existing folder with that name is reused). Files stay unfiled until you do this. * **Review status travels with the file.** The status you set on a canvas image or group (Approved, Pending, Rejected, Needs Review, In Progress) shows as a tag on the file here and can filter the page. It is a tag, not a gate: files without a status stay fully usable. * **How it was made.** Open any file and its **Details** card shows the model, aspect ratio and quality it was generated at — 1K / 2K / 4K for images, 720p / 1080p for videos — plus the clip length for videos and the exact pixel size when Memo recorded it, with when and by whom it was created. The same card appears wherever you open a generation: project assets, the Image and Video tools, and Workflow runs. * **What the picture shows.** When an image finishes, Memo looks at the result and writes down what is actually in it — the kind of image, the subjects and a one-line description. Search matches it, the expanded view shows it under **Shows**, and unfiled files get a hint such as "Looks like a character" to help you file them. * **Conflicts are visible.** If a file or folder changed since you read it, Memo asks you to review the latest version. Review badges change after the save succeeds. Reopening a canvas uses the latest saved file verdicts and authored names, including files outside the recent-generation feed. Saving canvas layout uses its version, so an older snapshot cannot replace a newer one. * **Characters keep their identity.** When you move a file into a folder named **Characters**, Memo asks which character it is: pick an existing Character from Assets to add the image to its sheet, or create a new one. Memo shows progress while saving a permanent sheet. A failed copy can be retried; a changed Character link is shown before you choose again. The sheet keeps its source record and survives deleting the original generation. The agent can ask for the Character by name in any project. * **Everything else you could do in the old Generations tab is still here:** open, download, delete, **Save as reference** and **Add to collection**. Your connected agent reads folder counts and a size-limited file page with `get_project`, follows `list_project_files` to read more, creates folders with `create_project_folder`, and files outputs with `move_generations` and a `folder_id`. It can edit file details through `update_generation`; see [Connect Your Agent](/get-started/connect-your-agent) for revisions, full details and run records. ## Sending inspirations to Studio From your library, right-click any inspiration and select **Send to Studio** (or use the action button in the detail modal). Memo creates a new project pre-loaded with that inspiration on the canvas — ready for the agent to use as a reference. ## Filing generations into collections In a project's assets page, hover any completed image or video and choose **Add to collection** (also in the expanded view's action bar). Memo copies the result into your library and files it in the collection you pick, so the reference stays available even if you later delete the project. Each generation maps to one library item — no duplicates when you file it in several places. See [Collections](/save-organize/collections). ## Cost Image generation, video generation, and agent chat all consume credits. A credit pill in the Studio header shows your current balance with a hover tooltip breakdown. When credits are low, pre-action warnings appear. When exhausted, an upgrade prompt. The system tracks cost per project, so you can see exactly what each campaign is costing. ## Mobile Studio requires a desktop-sized screen. On mobile or tablets (under 900px or coarse pointer), you'll see an interstitial with a link back to the home grid. # Simple vs Memo Magic Source: https://docs.memo.solutions/studio/prompt-modes How Memo processes your prompts before generating — when the AI enhances what you write vs. when it sends your exact words verbatim. Every generation in Studio runs through one of two prompt-processing modes. You toggle between them in the chat settings menu. ## Memo Magic (default) The agent takes your prompt and enhances it before calling the image model. A short request like "a bar of soap" becomes a rich, cinematic prompt with composition, lighting, camera angle, textures, and atmosphere — structured using the Nano Banana framework that the image model responds best to. **Use Memo Magic when you want:** * Production-quality results from short prompts * The agent to act as a creative director * Cinematic polish without having to write it yourself **Example:** * You type: `a bar of soap` * Memo Magic sends: a full structured prompt with subject, composition, lighting setup, camera/lens choice, and style direction tuned to what that subject needs ## Simple The agent sends your exact words to the image model, verbatim. No rewriting, no embellishment, no added detail. What you type is what the model sees. **Use Simple when you:** * Are testing prompt fidelity * Have written a carefully-crafted prompt yourself * Want full control over every word * Are comparing model behaviour for the same raw input **Example:** * You type: `a bar of soap` * Simple sends: `a bar of soap` ## Confirmed briefs always use Memo Magic Simple mode only applies to direct, single-shot prompts. When you confirm a [creative brief](/studio/creative-briefs) — whether it's a parallel campaign or a sequential storyboard — the agent's crafted scene prompts are always used, because the brief is the prompt you co-wrote and confirmed with the AI. Toggling Simple on doesn't downgrade your confirmed brief back to the raw sentence you started with. This means: * **Single prompt + Simple on** → your words, verbatim * **Single prompt + Memo Magic on** → AI-enhanced prompt * **Confirmed brief (any toggle, any continuity mode)** → the brief's crafted per-deliverable prompt ## Switching between modes The toggle lives in the Studio chat settings, next to the model selector and the [Create / Brainstorm mode](/studio/brainstorm-mode) toggle. It persists across turns in the same conversation but doesn't affect previously-generated images. Changing the mode mid-conversation only affects future generations. Your existing nodes stay exactly as they were generated. # Skills Source: https://docs.memo.solutions/studio/skills Reusable creative recipes with focused playbooks, supporting references, and a clear draft-to-ready workflow. A **skill** is a reusable creative recipe — a named markdown playbook the agent follows end-to-end when you invoke it. Think of it as a prompt template with teeth: structured enough that the agent executes it reliably, flexible enough that you can still hand it new subjects and contexts. Good candidates for skills: * A "hero shot" recipe that always produces the same composition, lighting, and finish * A "story reel" that always builds a 4-scene narrative from a single product * A "platform pack" that turns one idea into Instagram square + Reel + LinkedIn variants * A "brand audit" that runs a consistent visual analysis across saved inspirations If you're copy-pasting the same multi-step prompt more than twice, it belongs in a skill. ## Where skills live Open **Assets → Skill library**. General skills, brand-owned skills, and Memo starters share this library. Filter by location and **All statuses / Ready / Drafts**. Brand Kits also have a **Guidance & skills** view. Collections contain **Images** and **Rules**; they do not own or recommend skills. Two ways to view the library, switchable with the **Grid / List** toggle next to search: * **Grid** — compact entries arranged in two columns at wide desktop widths, showing an image or icon, name and use description. Relevant brand and draft labels stay visible. * **List** — the same compact entries in one column, with a row menu (⋯) for **Open** and **Delete**. Your layout choice is remembered per browser. Skills created by a connected agent remain attributed to whoever connected it in the saved record. From here you can: * **Create** with the **New skill** header button. * **Read** a skill, then choose **Edit** to change its instructions, references or location. * **Search** by name or content as the library grows. * **Delete** skills you do not use, after confirmation. When the library is empty, the **Create Skill** action appears directly in the first-run state so there is still one obvious way forward. ## Memo-official starters Every workspace ships with a starter pack authored by **Memo**. They sit in the same library, are read-only (open one and **Duplicate** it to make your own version), and connected agents get them through `list_skills` / `get_skill` like any other skill: * **Naming Convention** — the tag grammar and never-overwrite rules that keep a multi-asset production findable. * **Scene Engine** — stress-test a scene or sequence against Goal, Obstacle, Tactic, Reversal, Value Shift before spending credits. * **Acting Task** — direct character performance with playable tasks instead of emotion labels. * **Blocking Map** — exact multi-character staging via a color-coded schematic sent as a reference. * **CINEDANCE** — production-ready cinematic video prompts: references, blocking, optics, physics, lighting. * **Motion Design** — render-ready 15-second launch and motion-graphics video prompts: one core mechanic, locked palette, beat sheet, copy-list contract, fully silent. ## The editor Open a skill to read its description and instructions. Choose **Edit** to make changes. Memo starters and skills opened by viewers remain read-only. Choose **New skill** to create one. The main form has three fields: * **Name** — a short title you can recognize and select in chat. * **Use this skill for** — one sentence describing when it is useful, such as “summer menu photos for social media.” Agents see this description when discovering skills; it is not an automatic trigger. * **Instructions** — what to do and what the result should be. Plain English is fine. Type `@` to reference brand assets, colors or instructions. **Images (optional)** lets you attach images the skill should use each time. Leave it empty for a text-only skill. Brand assets attach directly; picks from Generations or Inspirations are first saved as brand assets. **More options** holds the less common controls: an optional **Expected result**, **Saved in** location, extra notes, organization tools and a preview of what the agent receives. Creating from a Brand Kit already selects that brand. Moving a skill keeps its instructions and references; if it has fixed images, review those before changing brands. Older collection associations and subject labels are preserved as inactive metadata and do not control skill availability. Put requirements that always apply in rules, instructions for this particular task in the skill, and detailed examples in extra notes. Choose the model where you generate; existing saved model pins are preserved. ### Saving and long instructions **Save skill** makes a new skill available after checking its use description, nonempty instructions, references and size limits. The separate expected-result field is optional: describe the result in Instructions. **Save draft** keeps unfinished work out of the agent's runnable library. Older skills retain their existing compatibility when saved. There is no minimum word or step count. Available new skills allow **12,000 characters** of instructions; drafts allow **50,000**. Extra notes allow **12 entries**, **20,000 characters each**, **100,000 total**. The use description allows **500 characters**; the optional expected result allows **2,000**. Text is never silently cut to fit. For a 20,000-character source, save a draft. A warning points you to **More options → Organize long instructions → Separate extra notes**. This proposes moving recognizable Examples, References, Background and Notes sections verbatim. Review the proposal, then **Apply organization** or **Keep original**. You can also move an exact passage manually. No model runs and no credits are spent. **Show what the agent receives** previews the instructions and reference catalog. It does not test output quality. Failed saves keep your edits. If another editor changed the skill, reconcile with the latest version before saving again. ### Ask the agent instead In Studio chat, select an image on your canvas and ask the agent to turn it into a skill ("save this as a reusable recipe"). **Save Skill** puts the proposed recipe in your library as a draft. Open it to review its use description, instructions and references, then choose **Save skill**. ## Invoking a skill Two ways to call a skill in Studio chat: ### Slash command Type `/` in the composer. A picker appears showing available skills (and [Workflows](/studio/workflows) when enabled), filtered as you type. Drafts are excluded and cannot be invoked through a stale picker selection. ``` /hero-shot for the new soap bar, clean studio look ``` The agent reads the playbook as the brief for the turn — your free-text addition is the subject. Referenced images are injected automatically: the agent *sees* them, and their IDs are attached to every generation server-side, so brand consistency doesn't depend on the model remembering. ### @mention Type `@` followed by a skill name — useful when combining a skill with a brand kit mention in one message (`@Acme Brand @story-reel ...`). ## Plan-then-execute For skills that produce multiple deliverables (a storyboard recipe, a platform pack), the agent **proposes a numbered plan first** — usually as a creative brief on your canvas. You review, adjust ratios and references, and click Generate. The skill's prose controls the plan; your confirmation controls execution. Skills slot neatly into the [Creative Brief flow](/studio/creative-briefs). ## How aspect ratio and quality get chosen Skills hold the *creative intent* — style, references, directions. They don't hold a fixed aspect ratio or quality, so one `/hero-shot` can produce a 1:1 feed post AND a 16:9 banner: * **Single-output skills** — the agent asks once for ratio and quality, then generates. If the playbook already specifies a ratio ("produce a vertical 9:16"), it skips the question. * **Multi-deliverable skills** — the agent builds a brief with one deliverable per output, each with its own ratio and quality row, enforced server-side at generation. ## Combining skills with brand kits A **General** skill works with any brand: @mention a kit in the same message and the skill provides the recipe while the kit provides the identity. ``` @Acme Brand /hero-shot a new packaging drop ``` A **brand skill** belongs to that Brand Kit and is labeled accordingly. Keep reusable task instructions here, and put collection-specific requirements in the collection's **Rules**. For example, a product-photography skill explains how to compose a shot; a device collection rule says where its logo must appear. ### How the agent chooses During Studio planning, the agent receives a small catalogue of available workspace and current-brand skills: names and short use descriptions, up to 24 at a time. Drafts and other brands are excluded. It compares these descriptions with your request, reads the chosen instructions with `get_skill`, and can fetch extra notes only when needed. It can search or page through more choices with `list_skills`; it may use no skill when none fits. Selecting a collection changes the applicable rules, not the skill pool. The agent still has to follow those rules when it uses a skill. Reading a skill does not start or approve a generation. An automatically chosen recipe gives the agent reference IDs to include when generating; the explicit slash-command path above also attaches its saved images server-side. ## Skills over MCP Connected agents (Claude, or anything speaking MCP) work with the same library: * `list_skills` returns paginated lightweight summaries with a Brand Kit filter, excluding drafts from runnable discovery. * `get_skill` returns the chosen core playbook and a supporting-reference catalog. It does not append all supporting text. * `get_skill_resource` reads one supporting reference in bounded chunks, with an explicit continuation when needed. * `create_skill` / `update_skill` let an agent capture a workflow you refined in conversation, or improve an existing playbook — attributed to you in the saved record. Updates keep an automatic copy of the previous version, so an agent rewrite is never a one-way door. This is the same skill either way: edit it in the app, run it from an agent, or the reverse. New MCP-created skills default to draft. Agents can explicitly request ready status with the required use description and bounded instructions. Updates to existing skills preserve omitted configuration fields, including inactive legacy collection associations and supporting references. New collection associations are rejected. ## Editing skills Changes apply to future invocations immediately — already-generated work doesn't change. If a skill produces inconsistent output, tighten its prose: be specific about deliverable count, style anchors, and required references. Open the skill, then choose **Edit**. Images and extra notes stay attached when you save. ## Tips * **Start from a prompt you've already perfected.** If a multi-step prompt keeps working, paste it into a skill and name it. * **Make skill names short.** You'll type them after a slash. `/hero-shot` beats `/product-hero-shot-three-angles`. * **Keep each skill single-purpose.** One recipe per skill. If it's drifting into "and also does X," split it. * **Write the playbook in the agent's voice.** Be specific about what to produce; leave room in *how*, so your brand kit can do its job. * **Attach the concrete references.** If the prose mentions "the character" or "the product," make sure that image is actually attached — otherwise the agent has prose pointing at nothing. * **Separate requirements from procedure.** Store brand-wide requirements in the Brand Kit's rules. Keep steps for this particular recipe in the skill, and detailed examples in supporting references. * **Test each skill with two different subjects** before relying on it. If output quality differs wildly between subjects, the prose needs tightening. # Workflows Source: https://docs.memo.solutions/studio/workflows Reusable generation recipes — save a working canvas setup once, run it again on any brand, and explore official starters. Workflows is switched off for beta workspaces for now. This page describes the feature as it runs on our internal sandbox; it opens to everyone once it is ready. A Workflow is a saved, reusable generation recipe: the scenes, prompts, and reference slots of a canvas setup, packaged so it can be run again with new inputs. Build something that works once — a product-shot pipeline, a character sheet, a format converter — and stop rebuilding it by hand. Find them under **Workflows** in the sidebar. The **List / Grid** switch beside **Explore / My workflows** chooses preview cards or compact rows. Your browser remembers this preference; search and category filters work in both layouts. Rows retain the available edit and management actions. Select anywhere on a Workflow card to open it. Cards share the landscape layout used by Studio projects and Collections, with the description directly beneath the title. ## Explore starters The **Explore** tab ships official, ready-to-run starters, each with example output so you can see what it produces before spending credits: * **Character Sheet** — turn a single character reference into a consistent multi-view sheet (chained scenes keep the character identical across poses). * **Aspect Ratio Converter** — take an image and re-frame it cleanly across aspect ratios instead of cropping. More starters land over time. Running a starter copies it onto your canvas wired up and ready — drop in your references, press Execute. ## Running a Workflow 1. Open a Workflow and fill its reference slots (the images or assets it needs). 2. Review the credit estimate — every Workflow prices itself before running. 3. Execute. Each scene generates in order, and outputs land on your canvas like any other generation. ### Choosing your outputs You don't have to run everything a Workflow makes. The run panel lists every output by name — untick the ones you don't need and the run only generates (and only charges for) what's selected. Each row shows its own price and the estimate updates as you pick. One rule keeps quality honest: if a sheet is built from another output (the Character Sheet's sheets are all built from the Turnaround), that reference stays locked in and is delivered with your run — you pay for it, you get it. ### Choosing a model Some Workflows offer a **Model** picker in the run panel — a short, curated list of models the recipe has been tested on. The Character Sheet starter, for example, runs on **Nano Banana 2** by default or **Seedream 5.0 Pro** for a premium finish at a higher credit cost. Pick a model and the per-output prices and the estimate update instantly, so the trade-off is always visible before you generate. Workflows without a picker always run on their tuned default. If a model can't produce one of a Workflow's outputs (the Aspect Ratio Converter's 4:5 frame doesn't exist on GPT Image 2, for instance), that output is simply disabled while the model is selected — shown, not hidden, and never silently produced at the wrong ratio. You're only charged for what actually runs. ## Runs — your results, kept Every run from a Workflow's page is saved automatically. Nothing is lost when you navigate away: * **Runs history** — each Workflow's page keeps a **Runs** section: every past run, newest first, with the inputs it used. Come back anytime; your results are waiting. * **Per-result actions** — click any result to view it full-size, download it, delete it, or **save it to Assets** so it becomes a reusable brand reference. * **Save as character** — on character workflows (like the Character Sheet starter), one click saves a whole run as a single character collection in **Assets → Characters**: the turnaround becomes the cover, the other sheets ride along. * **Download all** — one click zips a run's outputs, named by scene (e.g. `poster-9-16.png`), ready to hand off. * **Studio → Generations** — the same results also appear in the **Workflow runs** project alongside the rest of your generations. ## Saving your own Build the setup on the Studio canvas, then save it as a Workflow. It gets its own slug, shows up in your Workflows list, and anyone in the workspace can run it. If **My workflows** is empty, its first-run state links straight to **Open Studio**. The Workflow illustration is interactive: hover it for the same responsive line-motion language used across Memo's other empty libraries. ## Editing a Workflow Everything lives on the **Workflows** page: browse **Explore** and **My workflows** as a gallery or a compact list (the view toggle sits beside the tabs). Clicking a Workflow opens it ready to run; **Edit** lives in its card's ⋯ menu, and as an **Edit** button on the Workflow's own page. Official Memo starters can't be edited — run them as-is, or switch to their **Canvas** view and copy the board into your own Studio: that copy is fully yours to change and re-save as your own Workflow. The editor has three tabs: * **Setup** — rename the Workflow, describe what it makes, and set **Rules**: firm constraints (one per line, e.g. "Never redraw the logo") appended to every output's prompt. * **Inputs** — the images someone provides when they run it. Rename each input, swap its default image, and give it a **role** that tells the model how faithfully to treat it: * **Preserve exactly** — reproduce the image as provided; for logos, products, packaging. Never redrawn or restyled. * **Style reference** — copy the image's look, mood, and palette, never its subject or content. * **Subject** — place it as the subject of the scene, kept clearly recognizable. * **Outputs** — one card per generated image or video, each with an example thumbnail when available. Edit titles and prompts freely; format settings (aspect ratio, quality, duration) are frozen from the source brief — restructure by re-saving from an edited brief. An output's **Uses** row shows what it receives. Besides the Workflow's inputs, **output of…** chains an *earlier output's generated result* in as an extra input — the way the Character Sheet's pose sheets build on its Turnaround. Chained outputs always run after the output they build on; when a Workflow chains, the Outputs tab opens with a **How it runs** map showing the steps at a glance. Not sure what the model will actually be told? Every output card has a **Final prompt** toggle that shows the exact composed prompt — your prose, the Rules block, and each input's role instruction — updating live as you type. ## Workflows vs. Skills * **Skills** are written playbooks — instructions and know-how the agent reads and applies while working with you. * **Workflows** are executable recipes — a fixed sequence of generation scenes with defined inputs that runs the same way every time. Use a Skill to teach the agent *how* to think about your brand; use a Workflow to make a *repeatable deliverable* one click. ## From an agent Connected agents (see [Connect Your Agent](/get-started/connect-your-agent)) can list your Workflows and run them: `list_workflows` shows each recipe and its reference slots, `run_workflow` prices a run, and only an explicit confirmation spends credits. # Creating & Joining Workspaces Source: https://docs.memo.solutions/workspaces/creating-and-joining Set up a workspace for your team or join an existing one via invite. Workspaces are the container for everything in Memo. Every inspiration, generation, and brand kit in Memo lives inside a workspace. Workspaces are how you collaborate, how access is scoped, and how billing is metered. ## What a workspace contains A workspace owns: * All saved inspirations and generations * All brand kits and brand assets * All Studio projects * Its member list, roles, and invites * Its billing plan and credit balance Workspaces are private to their members. No public surface. If you want someone to see your work, you invite them. ## Creating a workspace When you sign up, Memo creates one automatically. You can create additional workspaces at any time — one for personal work, one per client, one per project. Free plan limits you to 1 owned workspace. Pro removes the limit. ### When to use multiple workspaces * Different clients or teams who shouldn't see each other's content * Personal experiments separate from client work * A specific project that needs its own brand kit, library, and member list * Trying out Memo with a small team before rolling it out broadly For solo work, one workspace is usually enough. ## Joining a workspace Someone shares an invite link — via email, Slack, or direct message. Each invite shows the workspace name, logo, and the role you'll be assigned. ### If you already have a Memo account 1. Click the invite link 2. See the workspace details — name, logo, your assigned role 3. Click **Accept Invite** 4. "You're In!" — redirected to the workspace dashboard ### If you're new to Memo 1. Click the invite link 2. Click **Sign in to Accept** 3. Create an account (email or Google) 4. You're returned to the invite page — accept in one tap ### What happens after * You're added as a member with the role from the invite * The workspace appears in your workspace switcher in the sidebar * You can immediately see all content in that workspace * You don't lose access to any other workspaces you belong to ## Switching between workspaces The workspace switcher in the sidebar shows where you are. Click it to see all your workspaces and switch instantly — the view re-renders with the new workspace's content. ## Roles | Role | View | Edit content | Manage members | Billing & delete | | ---------- | ---- | ------------ | -------------- | ---------------- | | **Viewer** | Yes | — | — | — | | **Editor** | Yes | Yes | — | — | | **Admin** | Yes | Yes | Yes | — | | **Owner** | Yes | Yes | Yes | Yes | One owner per workspace — the person who created it. Ownership can't be transferred. ## Tips * **Single seat today.** Free, Studio, Pro, and Max are solo plans. One workspace, one member. Shared multi-seat workspaces are part of the team plans, which come later. * **The workspace URL is permanent.** Auto-generated from the name at creation, can't be changed — because that would break any links you've shared. * **Invites don't expire.** Accept weeks later, as long as the admin hasn't cancelled. * **You can be in multiple workspaces.** Joining one doesn't remove you from any other. ## Troubleshooting **The invite link says "Invalid Invite."** The link may have been cancelled or is malformed. Ask for a fresh one. **I clicked accept but nothing happened.** Refresh and try again. The workspace might be at its seat limit — ask the admin to free a seat or upgrade. **I can't see the workspace after accepting.** Refresh your browser. Check the workspace switcher in the bottom-right. If it still doesn't show, sign out and back in. **I joined the wrong workspace.** Ask the owner or admin to remove you from the Members view. There's no self-leave action yet. # Members & Roles Source: https://docs.memo.solutions/workspaces/members-and-roles Invite teammates, change roles, manage pending invites — all from one Members view. The Members view is the single place to see everyone in your workspace and everyone you've invited. It lives at **Manage Workspaces → Members** — joined members at the top, pending invites below. Only **admins** and **owners** can invite or change roles. Editors and viewers see the same list without management actions. ## Inviting a member 1. Open the workspace switcher in the sidebar → **Manage Workspaces** 2. You're on the Members tab by default 3. Click **Invite Member** 4. Enter email and pick a role (Viewer, Editor, or Admin — Owner can't be assigned) 5. Click **Create Invite** What happens: * An **invite email** is sent, branded with your workspace name and logo * A **success card** shows the invite link in a copyable code box — share via Slack or DM if you prefer * The invite appears in **Pending invites** * A seat is consumed immediately, even before they accept Click **Invite another** in the success card to send a second invite without closing the modal. ## Pending invites Below joined members, admins see **Pending invites (n)** — each row shows: * The invitee's email and assigned role * A **Copy link** button (brief checkmark feedback on copy) * A **trash icon** to cancel the invite and free the seat The section disappears when all invites have been accepted. ## Changing a role 1. Find the member in the list 2. Click their role badge — it becomes a dropdown 3. Pick a new role 4. Confirm in the modal (it explains what the new role can do) You can't change the owner's role or your own. Admins can promote/demote editors and viewers but can't promote anyone to admin — only the owner can. ## Removing a member 1. Find the member 2. Click the kebab menu (⋮) 3. Click **Remove from workspace** 4. Confirm Access revoked immediately. You can't remove yourself — ask the owner to remove you if needed. ## Tips * **Inviting an existing member returns a clear error.** No stale duplicates. * **No resend button** — cancel the pending invite and create a new one. Takes about 4 seconds. * **Email failures don't block invites.** The link still works. Share it directly if the email didn't arrive. * **Pending invites count against seats.** At the cap? Cancel old invites or upgrade. ## Troubleshooting **The invite email never arrived.** Check spam. If not there, copy the link from Pending invites and send directly. **"This user is already a member of the workspace."** They're already in. Check the Members section above the invite form. **"There is already a pending invite for this email."** You've already invited them. Find the pending invite, copy the link, resend directly. **Seat limit error when inviting.** All seats used (including pending invites). Cancel a pending invite or upgrade your plan. # Workspace Settings Source: https://docs.memo.solutions/workspaces/workspace-settings Rename, describe, brand, and (if you mean it) delete your workspace. Settings live at **Manage Workspaces → Settings**. Only **admins** and **owners** see this tab. All fields save automatically on blur — no "Save" button. Type and move on. ## What you can change * **Name** — shows in the workspace switcher and card header (1–50 characters) * **Description** — short blurb under the name (max 280 characters, with live character count) * **Logo** — the image used in the switcher pill, card header, members list, and invite page * **Workspace URL** — read-only, displayed for reference ## Renaming Two ways: **Inline (fastest):** On `/workspaces`, hover the workspace name → pencil icon → type → Enter to save, Escape to cancel. **Settings tab:** Edit the Name field, click outside. Both call the same backend, same result. ## Logo 1. Click **Upload logo** (or **Replace logo** if one exists) 2. Pick an image — PNG, JPG, or SVG, max 5 MB 3. The logo appears immediately across the workspace switcher, card header, workspace list, and invite page Click **Remove** to go back to the default Memo icon. Logos look best as squares. Memo crops to a rounded square at 64x64. Wider images get center-cropped. ## Workspace URL Something like `memo.app/w/your-slug`. Read-only by design — changing slugs would break links you've shared. Auto-generated from the name at creation. Copy it with the button next to it. ## Deleting a workspace **Owner only.** Admins cannot. 1. Scroll to the **Danger Zone** 2. Click **Delete Workspace** 3. Type the exact workspace name to enable the button 4. Click **Delete Workspace** (red) This is permanent and cascades through everything: * All members removed * All pending invites cancelled * All inspirations, generations, brand kits, brand assets, and Studio projects deleted After deletion: if you have other workspaces, Memo switches to one. If this was your only one, your account starts over as new: the next visit takes you back through setup from the beginning, and your Getting Started progress resets. There is no undo. The data does not go to a trash bin. ## Troubleshooting **Settings tab isn't showing up.** You're not an admin or owner. Ask an admin if you need a setting changed. **Delete button won't activate.** Type the workspace name exactly — capitalization and spaces matter. **Logo upload failed.** Check the file: must be an image, max 5 MB. Try a PNG at \~512x512. **Deleted by mistake.** No recovery. Workspace deletion is intentionally final. Create a new one and re-invite.