GET
/v1/schemas/fal/image/blackforestlabs%2Fflux-3%2Fklein%2Fbase%2Ftext-to-image%2Flora
Accept:
Request body
13 properties · 1 required · 4 $defs| property | type | description | constraints |
|---|---|---|---|
| prompt* | string | The prompt to generate an image from. The model is trained on detailed captions: describe framing, subject, background and lighting. | |
| 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 |
| image_size | ImageSize | enum | The size of the generated image. Each side can be 256 to 4096 pixels (native 4K). | default: "square_hd" |
| num_inference_steps | integer | The number of inference steps to perform. | 4 ≤ n ≤ 50 · default: 50 |
| loras | LoRAInput[] | LoRA weights to apply (maximum 3). | items ≤ 3 · default: [] |
| num_images | integer | The number of images to generate. | 1 ≤ n ≤ 4 · default: 1 |
| 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 |
| bounding_boxes | BoundingBox[] | Optional layout: draw each described object inside its box. Box edges are fractions of the image size, with (0, 0) at the top-left. Name boxes in the prompt by label, e.g. `A red fox <fox> sits under a red umbrella <umbrella>`. | items ≤ 32 · nullable |
| 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 |
| guidance_scale | number | How closely the model should stick to your prompt (classifier-free guidance). | 0 ≤ n ≤ 20 · default: 3.5 |
| 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 |
| negative_prompt | string | The negative prompt to use. Use it to address details that you don't want in the image. | default: "" |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"blackforestlabs/flux-3/klein/base/text-to-image/lora","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}