GET
/v1/schemas/fal/image/fal-ai/uso
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above.Source trace89dad651e7bd67f3f4a3517c3ac2b691db84c861b5b670ccb9275b2bc150bc6f{
"fetchedAt": 1783331098,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
12 properties · 1 required · 1 $defs| property | type | description | constraints |
|---|---|---|---|
| input_image_urls* | string[] | List of image URLs in order: [content_image, style_image, extra_style_image]. | |
| seed | integer | Random seed for reproducible generation. Use same seed for consistent results. | nullable |
| num_inference_steps | integer | Number of denoising steps. More steps can improve quality but increase generation time. | 1 ≤ n ≤ 50 · default: 28 |
| output_format | enum | Output image format. PNG preserves transparency, JPEG is smaller. | jpeg | png · default: "png" |
| guidance_scale | number | How closely to follow the prompt. Higher values stick closer to the prompt. | 1 ≤ n ≤ 10 · default: 4 |
| image_size | ImageSize | enum | The size of the generated image. | default: "square_hd" |
| prompt | string | Text prompt for generation. Can be empty for pure style transfer. | default: "" |
| enable_safety_checker | boolean | Enable NSFW content detection and filtering. | default: true |
| negative_prompt | string | What you don't want in the image. Use it to exclude unwanted elements, styles, or artifacts. | default: "" |
| num_images | integer | Number of images to generate in parallel. | 1 ≤ n ≤ 4 · default: 1 |
| keep_size | boolean | Preserve the layout and dimensions of the input content image. Useful for style transfer. | default: false |
| sync_mode | boolean | If `True`, the media will be returned as a data URI and the output data won't be available in the request history. | default: false |
Types
1 $defsImageSizeobject
| width | integer | The width of the generated image. | 0 < n ≤ 14142 · default: 512 |
| height | integer | The height of the generated image. | 0 < n ≤ 14142 · default: 512 |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/uso","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}