GET
/v1/schemas/fal/image/fal-ai%2Fflux-lora-fill
Accept:
Request body
16 properties · 2 required · 3 $defs| property | type | description | constraints |
|---|---|---|---|
| mask_url* | string | The mask to area to Inpaint in. | |
| image_url* | string | URL of image to use for fill operation | |
| enable_safety_checker | boolean | If set to true, the safety checker will be enabled. | default: true |
| seed | integer | The same seed and the same prompt given to the same version of the model will output the same image every time. | nullable |
| image_size | ImageSize | enum | The size of the generated image. | |
| 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 |
| fill_image | ImageFillInput | Use an image fill input to fill in particular images into the masked area. | nullable |
| num_inference_steps | integer | The number of inference steps to perform. | 1 ≤ n ≤ 50 · default: 28 |
| output_format | enum | The format of the generated image. | jpeg | png · default: "jpeg" |
| prompt | string | The prompt to generate an image from. | default: "" |
| resize_to_original | boolean | Resizes the image back to the original size. Use when you wish to preserve the exact image size as the originally provided image. | default: false |
| loras | LoraWeight[] | The LoRAs to use for the image generation. You can use any number of LoRAs and they will be merged together to generate the final image. | default: [] |
| acceleration | enum | Acceleration level for image generation. 'regular' balances speed and quality. | none | regular · default: "none" |
| guidance_scale | number | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. | 28 ≤ n ≤ 35 · default: 30 |
| num_images | integer | The number of images to generate. This is always set to 1 for streaming output. | 1 ≤ n ≤ 4 · default: 1 |
| paste_back | boolean | Specifies whether to paste-back the original image onto to the non-inpainted areas of the output | default: true |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/flux-lora-fill","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}