Skip to main content

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 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, 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 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.