GET
/v1/schemas/fal/image/fal-ai/kling-image/o3/image-to-image
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source trace78b2bebbc4ae97ef8310c6b8c014b815a788c27d343e5d979763d921c8befea3{
"fetchedAt": 1791522002,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
11 properties · 2 required · 1 $defs| property | type | description | constraints |
|---|---|---|---|
| image_urls* | string[] | List of reference images. Reference images in prompt using @Image1, @Image2, etc. (1-indexed). Max 10 images. | |
| prompt* | string | Text prompt for image generation. Reference images using @Image1, @Image2, etc. (or @Image if only one image). Max 2500 characters. | length ≤ 2500 |
| resolution | enum | Image generation resolution. 1K: standard, 2K: high-res, 4K: ultra high-res. | 1K | 2K | 4K · default: "1K" |
| num_images | integer | Number of images to generate (1-9). Only used when result_type is 'single'. | 1 ≤ n ≤ 9 · default: 1 |
| enable_safety_checker | boolean | Authorized callers may set false to request relaxed screening. | default: true |
| sync_mode | boolean | If `True`, the media will be returned as a data URI. | default: false |
| result_type | enum | Result type. 'single' for one image, 'series' for a series of related images. | single | series · default: "single" |
| aspect_ratio | enum | Aspect ratio of generated images. 'auto' intelligently determines based on input content. | 16:9 | 9:16 | 1:1 | 4:3 | 3:4 | 3:2 · +3 more · default: "auto" |
| series_amount | integer | Number of images in series (2-9). Only used when result_type is 'series'. | 2 ≤ n ≤ 9 · nullable |
| output_format | enum | The format of the generated image. | jpeg | png | webp · default: "png" |
| elements | ElementInput[] | Optional: Elements (characters/objects) for face control. Reference in prompt as @Element1, @Element2, etc. | nullable |
Types
1 $defsElementInputobject
Element input for image generation with face/character control.
| reference_image_urls | string[] | Additional reference images from different angles. 0-3 images supported. Optional. | nullable |
| frontal_image_url | string | The frontal image of the element (main view). Optional. | nullable |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/kling-image/o3/image-to-image","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}