domains / families / media / create-image-fal

create-image-fal

separate

Generate or edit an image via any FAL image model (nano-banana edit, gpt-image, flux, ...), routed through the GooseWorks proxy, so the call is charged to your GooseWorks credits. image_urls must be public URLs; --image puts a local file on the fal CDN first. The recipe names the model + prompt. Use for keyframes, flat-cover transforms, product hero edits. (For the OpenAI gpt-image family specifically, create-image-gpt-image-fal also exists.)

When to use

• Generate or edit an image via any FAL image model
• Keyframes
• Flat-cover transforms
• Product hero edits
• Prompt-driven edit
• Restage or scene swap
• Subject swap in the same pose
• Product placed into a scene

When not to use

• Hand-writing a person prompt
• Using Nano Banana for real people or real products
• Using Flux for a face
• Asking for a blank pack of the advertised product
• Using prompts with 'unprinted', 'blank', 'unlabeled', 'no printed words', or 'back facing the camera' for brand products
• Using create-image-gpt-image-fal for lettering, logos, wordmarks, signage, or transparent cutouts

Skill page

Source