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.

​
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.

​
Grid presets

Grid presets are templated starting points — pre-written prompt structures organized by category. Select a preset, optionally adjust it, and generate. Each preset has:
  • A vision-analyzed, rewritten prompt template
  • Smart per-preset aspect ratio defaults
  • A quality picker (1K / 2K / 4K)
  • A searchable menu with auto-expanding categories
Presets give you consistent starting points while leaving room for creative direction.

​
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.

​
Video generation

The agent can also generate videos with control over:
  • Duration — 3s, 5s, 8s, 10s, or 15s
  • Aspect ratio — 16:9, 9:16, 1:1
  • 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.

​
Director mode

A cinematic style picker that gives the agent specific film and photography direction — lighting references, lens characteristics, color grading presets. Think of it as a shortcut to the visual language you’d use if you were directing a shoot.

​
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.