GET
/v1/schemas/fal/image/blackforestlabs/flux-3/klein/base/edit-image/lora
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source trace70bfcd4453549019f890ed8d5e6b0b9bd50d89f0f98bf1adc1bf915a94c2ed30{
"fetchedAt": 1793854802,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
14 properties · 2 required · 4 $defs| property | type | description | constraints |
|---|---|---|---|
| image_urls* | string[] | The reference images to edit or compose from (up to 10). | items ≥ 1 · items ≤ 10 |
| prompt* | string | A complete caption of the target image with the edit folded in. Refer to the references by their order: the first image, the second image. | |
| image_size | ImageSize | enum | The size of the generated image, 256 to 4096 pixels per side. If not set, a single reference image's own size (scaled to at most 4 megapixels) is used, or the first reference image's size (at most 1 megapixel) when several are given. | nullable |
| loras | LoRAInput[] | LoRA weights to apply (maximum 3). | items ≤ 3 · default: [] |
| 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 |
| negative_prompt | string | The negative prompt to use. Use it to address details that you don't want in the image. | default: "" |
| 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 |
| output_format | enum | The format of the generated image. | jpeg | png | webp · default: "png" |
| enable_safety_checker | boolean | If set to true, the safety checker will be enabled. | default: true |
| num_inference_steps | integer | The number of inference steps to perform. | 4 ≤ n ≤ 50 · default: 50 |
| enable_prompt_expansion | boolean | If set to true, the prompt is expanded into a detailed caption (grounded in the reference images when editing) before generation. | default: true |
| num_images | integer | The number of images to generate. | 1 ≤ n ≤ 4 · default: 1 |
| guidance_scale | number | How closely the model should stick to your prompt (classifier-free guidance). | 0 ≤ n ≤ 20 · default: 3.5 |
| bounding_boxes | EditBoundingBox[] | Optional layout, with (0, 0) at the top-left of each image: keep, move, resize or remove objects from the references, or place new ones. Name boxes in the prompt by label, e.g. `<dragon>`. | items ≤ 32 · nullable |
Types
4 $defsBoxobject
| x_min* | number | Left edge as a fraction of the image width (0-1). | 0 ≤ n ≤ 1 |
| x_max* | number | Right edge as a fraction of the image width (0-1). | 0 ≤ n ≤ 1 |
| y_max* | number | Bottom edge as a fraction of the image height (0-1). | 0 ≤ n ≤ 1 |
| y_min* | number | Top edge as a fraction of the image height (0-1). | 0 ≤ n ≤ 1 |
EditBoundingBoxobject
| source_box | Box | Where the object is in the reference image. Requires `source_image_index`. | nullable |
| source_image_index | integer | 0-based index into `image_urls` of the reference the object comes from. Leave unset for a new object. | n ≥ 0 · nullable |
| box | Box | Where the object goes in the output image, as on text-to-image. Use instead of `source_box`/`target_box`. | nullable |
| label | string | Short name for the object in this box, e.g. `dragon`. Write `<dragon>` in the prompt to tie the box to those words; a box the prompt doesn't name is added to the scene. Defaults to `obj_<n>`. | length ≤ 64 · nullable |
| target_box | Box | Where the object goes in the output image. Leave unset to remove a referenced object; set both boxes to move or resize it. | nullable |
| description* | string | What to draw in this box: the object and its look. | length ≤ 500 |
ImageSizeobject
| 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 |
LoRAInputobject
| scale | number | Scale factor for LoRA application (0.0 to 4.0). | 0 ≤ n ≤ 4 · default: 1 |
| path* | string | URL to a FLUX 3 Klein LoRA (.safetensors), e.g. from flux-3-image-klein-trainer. |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"blackforestlabs/flux-3/klein/base/edit-image/lora","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}