GET
/v1/schemas/fal/image/fal-ai%2Fboogu-image%2Fedit
Accept:
Request body
14 properties · 2 required · 1 $defs| property | type | description | constraints |
|---|---|---|---|
| image_url* | string | URL of the input image to edit. | |
| prompt* | string | The edit instruction describing how to transform the input image. Boogu-Image supports English and Chinese instructions. | |
| num_images | integer | The number of edited images to generate. | 1 ≤ n ≤ 4 · default: 1 |
| sync_mode | boolean | If true, the media is returned as a data URI and the output is not available in the request history. | default: false |
| num_inference_steps | integer | The number of denoising steps to perform. | 20 ≤ n ≤ 50 · default: 30 |
| image_guidance_scale | number | Reference-image guidance strength. A value of 1.0 disables image CFG; higher values preserve the input image more strongly. | 1 ≤ n ≤ 8 · default: 1 |
| negative_prompt | string | Describes what should NOT appear in the edited image. Used for classifier-free guidance; leave empty to disable text negative guidance. | default: "" |
| guidance_scale | number | Controls how closely the edit follows the text instruction. Higher values stick more closely to the prompt. | 1 ≤ n ≤ 8 · default: 4 |
| cfg_range_end | number | End of the timestep fraction over which CFG is applied. | 0 ≤ n ≤ 1 · default: 1 |
| image_size | ImageSize | enum | The output size. If omitted, the edited image follows the input image aspect ratio while respecting the model's 2K native limit. | nullable |
| output_format | enum | The format of the generated image. | jpeg | png · default: "jpeg" |
| enable_safety_checker | boolean | If true, the safety checker is run on the input and output images. | default: true |
| seed | integer | The same seed, prompt, and input image given to the same version of the model will output the same image every time. | nullable |
| cfg_range_start | number | Start of the timestep fraction over which CFG is applied. | 0 ≤ n ≤ 1 · default: 0 |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/boogu-image/edit","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}