GET
/v1/schemas/fal/video/fal-ai/wan/v2.2-a14b/image-to-video/lora
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above.Source trace13f7e98350290ebed0ed3816c1521bc566bacb26296847e5c8983908e8e3614b{
"fetchedAt": 1786338105,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
24 properties · 2 required · 1 $defs| property | type | description | constraints |
|---|---|---|---|
| image_url* | string | URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped. | |
| prompt* | string | The text prompt to guide video generation. | |
| enable_prompt_expansion | boolean | Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning. | default: false |
| num_interpolated_frames | integer | Number of frames to interpolate between each pair of generated frames. Must be between 0 and 4. | 0 ≤ n ≤ 4 · default: 1 |
| reverse_video | boolean | If true, the video will be reversed. | default: false |
| guidance_scale | number | Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality. | 1 ≤ n ≤ 10 · default: 3.5 |
| negative_prompt | string | Negative prompt for video generation. | default: "" |
| acceleration | enum | Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'. | none | regular · default: "regular" |
| enable_safety_checker | boolean | If set to true, input data will be checked for safety before processing. Disabling it requires account authorization; unauthorized requests are always checked. | default: false |
| shift | number | Shift value for the video. Must be between 1.0 and 10.0. | 1 ≤ n ≤ 10 · default: 5 |
| interpolator_model | enum | The model to use for frame interpolation. If None, no interpolation is applied. | none | film | rife · default: "film" |
| aspect_ratio | enum | Aspect ratio of the generated video. If 'auto', the aspect ratio will be determined automatically based on the input image. | auto | 16:9 | 9:16 | 1:1 · default: "auto" |
| enable_output_safety_checker | boolean | If set to true, output video will be checked for safety after generation. | default: false |
| resolution | enum | Resolution of the generated video (480p, 580p, or 720p). | 480p | 580p | 720p · default: "720p" |
| num_inference_steps | integer | Number of inference steps for sampling. Higher values give better quality but take longer. | 2 ≤ n ≤ 40 · default: 27 |
| loras | LoRAWeight[] | LoRA weights to be used in the inference. | default: [] |
| num_frames | integer | Number of frames to generate. Must be between 17 to 161 (inclusive). | 17 ≤ n ≤ 161 · default: 81 |
| seed | integer | Random seed for reproducibility. If None, a random seed is chosen. | nullable |
| frames_per_second | integer | Frames per second of the generated video. Must be between 4 to 60. When using interpolation and `adjust_fps_for_interpolation` is set to true (default true,) the final FPS will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If `adjust_fps_for_interpolation` is set to false, this value will be used as-is. | 4 ≤ n ≤ 60 · nullable |
| guidance_scale_2 | number | Guidance scale for the second stage of the model. This is used to control the adherence to the prompt in the second stage of the model. | 1 ≤ n ≤ 10 · default: 4 |
| video_quality | enum | The quality of the output video. Higher quality means better visual quality but larger file size. | low | medium | high | maximum · default: "high" |
| end_image_url | string | URL of the end image. | nullable |
| video_write_mode | enum | The write mode of the output video. Faster write mode means faster results but larger file size, balanced write mode is a good compromise between speed and quality, and small write mode is the slowest but produces the smallest file size. | fast | balanced | small · default: "balanced" |
| adjust_fps_for_interpolation | boolean | If true, the number of frames per second will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If false, the p… | default: true |
Types
1 $defsLoRAWeightobject
| scale | number | The scale of the LoRA weight. This is used to scale the LoRA weight before merging it with the base model. | 0 ≤ n ≤ 4 · default: 1 |
| path* | string | URL or the path to the LoRA weights. | |
| transformer | enum | Specifies the transformer to load the lora weight into. 'high' loads into the high-noise transformer, 'low' loads it into the low-noise transformer, while 'both' loads the LoRA into both transformers. | high | low | both · default: "high" |
| weight_name | string | Name of the LoRA weight. Used only if `path` is a Hugging Face repository, and required only if you have more than 1 safetensors file in the repo. | nullable |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/wan/v2.2-a14b/image-to-video/lora","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}