GET
/v1/schemas/fal/image/fal-ai%2Fflux-2-lora-gallery%2Fface-to-full-portrait
Accept:
Request body
12 properties · 1 required · 1 $defs| property | type | description | constraints |
|---|---|---|---|
| image_urls* | string[] | The URL of the cropped face image. | |
| acceleration | enum | Acceleration level for image generation. 'regular' balances speed and quality. | none | regular · default: "regular" |
| prompt | string | The prompt describing the full portrait to generate from the face. | default: "Face to full portrait" |
| num_images | integer | Number of images to generate | 1 ≤ n ≤ 4 · default: 1 |
| image_size | ImageSize | enum | The size of the generated image. If not provided, the size of the input image will be used. | nullable |
| num_inference_steps | integer | The number of inference steps to perform. | 4 ≤ n ≤ 50 · default: 40 |
| enable_safety_checker | boolean | Whether to enable the safety checker for the generated image. | default: true |
| seed | integer | Random seed for reproducibility. Same seed with same prompt will produce same result. | nullable |
| output_format | enum | The format of the output image | png | jpeg | webp · default: "png" |
| lora_scale | number | The strength of the face to full portrait effect. | 0 ≤ n ≤ 2 · default: 1 |
| sync_mode | boolean | If `True`, the media will be returned as a data URI and won't be saved in history. | default: false |
| guidance_scale | number | The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt. | 0 ≤ n ≤ 20 · default: 2.5 |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/flux-2-lora-gallery/face-to-full-portrait","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}