Creates a brand-new image from a text description, for subjects that do not exist yet or have to be made on purpose: bespoke scenes, branded visuals, concept art, icons, or hero imagery. In-image text such as signage, labels, and short copy renders legibly. Describe the subject, the scene, and any style or medium you want; you can choose an orientation and a standard or a high-fidelity 4K tier. This is text-to-image only, to change an image you already have, use restyle.
The subject does not exist yet and must be made (bespoke, branded, a specific scene).
Finding a real photograph, or changing an image you already have.
~300 credits / image (up to 1500)
A standard image is the usual case; a 4K render costs more, up to ~6000 cr.
Estimated; the actual charge depends on your input and is shown in the response.
Set these inside the intent when you run it.
What the image should show, in plain words.
Optional look or medium to honor, e.g. photoreal, illustration, 3D render.
Optional shape, one of square, portrait, or landscape.
A generated image as a downloadable file (a temporary hosted URL).
Run this sub-skill directly: pin it with operation and pass its inputs in the intent. (Omit operation and the Images skill will route from your intent instead.)
curl -X POST "https://skill.askfaro.com/skills/image/run" \
-H "Authorization: Bearer $FARO_TOKEN" \
-H "Content-Type: application/json" \
-d '{"intent":{"operation":"generate","description":"a red fox sitting in a snowy pine forest at dawn","style":"photoreal","aspect_ratio":"landscape"}}'Example requests