Most of the time you'll let the Agent handle generation — describe what you want and it picks the model and settings. But when you want direct control — an exact model, specific parameters, or precise inputs — Layer gives you a generation form you can drive yourself. It's the direct replacement for the old Layer's generation form.
Open the generation form
From inside any session, there are two ways in:
The bottom toolbar — click Generate image, Generate video, Generate 3D, Generate audio, or Generate playable.
The selector beside the chat box — switch from Agent to a direct generation mode.
The form opens above the toolbar, separate from the chat.
Generate directly
In the form, every choice is yours:
Model — pick the exact base model (e.g. FLUX.1 [dev])
Size & quality — resolution and aspect ratio (1K · 1:1) and quality (High)
Prompt — describe what you want to create
Reference sets — add sets to keep results on-style
Cost & count — see the CU cost up front and set how many to generate
Then hit generate. The result lands on the board, just like an Agent generation.
Edit an asset with a prompt
To tweak something you've already made — a prompt edit:
On the canvas, click an asset to select it (it shows up as a Selection chip next to the composer).
Open the image form and add it as the Source Image.
Type a prompt describing only the change — "make the liquid green," "add a soft glow" — and generate.
The model keeps your asset and applies just the change you asked for.
Generate video — choose your frames
Switch the form to Generate video and pick a video model. Depending on the model, you can directly set:
First Frame and Last Frame — anchor the clip to specific images, so you control exactly where the motion starts and ends
Reference sets — guide the overall look
Duration and aspect ratio
This is how you produce a specific chunk of video with precise control, rather than describing it and letting the Agent decide.
💡 The same form handles image, video, 3D, audio, and playables — switch modality from the bottom toolbar, then pick a model that fits.
Direct form vs. the Agent
Agent (chat): fastest for most work — describe the outcome and it handles model choice, prompt craft, and settings.
Generation form (direct): when you want exact control over the model, parameters, frames, or are reproducing a specific setup. It's the home for everything the old Layer's inference form did — now built into the session alongside your board.
What's next
Let the Agent do it → [Generate your first asset]
Get better results → [Writing better prompts]
Stay consistent → [Using reference sets]