Wayland on Flux
Wayland turns a rough sketch into a finished product shot, edits it, and remembers your taste.
“Turn this sketch into a product shot, warm up the light, and remember that I like warm tones.”
Examples. Names, prices and costs are illustrative.
Flux split the ask into jobs and sent each one to the model or tool that fits it. It picks among vetted models for each kind of task, cost-aware.
Generate the product shotLive
Images
Flux sent the sketch to an image model to draw the product shot.
Compare with the sketch in GeminiLive
Model
A model that can see compared the result with your sketch, to check the shape held.
Edit: warmer lightLive
Images
Edits go back to an image model, one change at a time.
Edit: softer shadowLive
Images
A second edit softened the shadow.
Remember: prefers warm tonesShipping
Memory
Flux saves the preference to memory, so the next shot starts warm, whichever model draws it.
Result Final shot saved. Warm tones are now your default, whichever model draws next.
Every call comes back with the model or tool that ran it and what it cost, all on one bill.
These costs are illustrative, not a quote. flux-auto bills each model step at the Standard rate, or the Fast rate when it sends the step to the Fast lane and a Fast model answers. Never more than Standard. Pin a model and you pay its own rate. See pricing
Example receiptIllustrative
| Step | Cost |
|---|---|
| Generate the product shotImages | $0.030 |
| Compare with the sketch in GeminiModel | $0.004 |
| Edit: warmer lightImages | $0.020 |
| Edit: softer shadowImages | $0.020 |
| Remember: prefers warm tonesMemory | $0.001 |
| One bill | $0.075 |
One key, any agent. If it can talk to OpenAI or Anthropic, it can connect to Flux.
Yes. Each edit goes back to an image model with the last version, so you can keep refining until it is right.
Not yet. Memory is shipping. Until then, put the preference in your agent’s instructions. The steps marked Live work today.
The costs on this page are illustrative, not a quote. flux-auto bills each model step at the Standard rate, or the Fast rate when it sends the step to the Fast lane and a Fast model answers. Never more than Standard. Pin a model and you pay that model’s own rate instead. Web, image, voice and app steps have their own prices.
One key for every model and tool in this example.