Promo image

Key art for a tool page, from a sentence.

What it takes

• A prompt (drafted for you from the tool's title and tagline)
• Optionally, one of the tool's screenshots to steer it

What it gives back

• One image, attachable as the tool's thumbnail or a screenshot in a click

What actually runs

• FLUX.1-dev, in fp8, on a ComfyUI worker.
• With a screenshot supplied the graph switches to image-to-image and the denoise slider decides how far it strays from it.
• The result is re-encoded through sharp before it is ever served, so nothing a worker returns reaches a browser as-is.

Worth knowing. Ask for one clear object, not a scene. Prompts that name a single focal subject beat prompts that describe a whole composition.

Running it

The .json attached to this listing is the graph itself — the one the Forge runs, not a tidied-up copy. Values in {{double braces}} are the placeholders filled in per job; replace them with real values and it runs in any ComfyUI new enough for the nodes it uses.

Full setup — the model manifest, the directories, the traps — is at /workflows/promo.

Licence and credit

The graph is ours and you may use it for anything, including commercially. The models it loads are not ours: each carries its own licence from whoever trained it, and that is the one that governs what you may do with the output.