GET
/v1/schemas/fal/image/fal-ai/krea-2/turbo/style
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above.Source trace30e75c5922616264684f65a5f160a3070a5f2c17a42bec6f7f6c6dd74986c2b2{
"fetchedAt": 1786338105,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
11 properties · 2 required · 1 $defs| property | type | description | constraints |
|---|---|---|---|
| reference_image_urls* | string[] | One to three image URLs used as style references. | items ≥ 1 · items ≤ 3 |
| prompt* | string | Base text description of the image to generate. | length ≥ 1 · length ≤ 5000 |
| acceleration | enum | The acceleration level to use for the image generation. | none | regular · default: "none" |
| output_format | enum | The format of the generated image. Default value: "png". | jpeg | png · default: "png" |
| 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 |
| seed | integer | Random seed for reproducible generation. Image *i* uses `seed + i`. | nullable |
| enable_safety_checker | boolean | If true, the output safety checker is enabled. Disabling it requires account authorization; unauthorized requests are always checked, and images flagged as unsafe are returned as black images. | default: true |
| enable_prompt_expansion | boolean | If true, the prompt is expanded with an LLM into a more detailed image-generation prompt for higher quality results. On failure, the original prompt is used unchanged. | default: false |
| image_size | ImageSize | enum | The size of the generated image. | default: "square_hd" |
| num_images | integer | The number of images to generate. | 1 ≤ n ≤ 4 · default: 1 |
| style_scale | number | Scale for the style adapter residual. | 0 ≤ n ≤ 4 · default: 1 |
Types
1 $defsImageSizeobject
| height | integer | The height of the generated image. | 0 < n ≤ 14142 · default: 512 |
| width | integer | The width 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/krea-2/turbo/style","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}