Genjutsu Motion Transfer
Transfer the movements from a source video to the person in reference photos
Request model |
Endpoint |
|---|---|
higgsfield/genjutsu-1.0-motion-transfer |
Video generation |
Input modes
| Mode | References | Reference roles |
|---|---|---|
reference Reference media |
2 to 11 | reference_image 1 to 10reference_video 1 |
Text is optional in these input modes on explicitly supported channels: reference
Prompt limit: 5,000 characters; longer prompts are rejected with 400.
Parameters
| Parameter | Description | Values | Default | Required |
|---|---|---|---|---|
duration |
Duration: Output video duration in seconds. | 1 to 30 |
5 |
No |
resolution |
Resolution: Output resolution. | 480p, 720p, 1080p |
720p |
No |
aspect_ratio |
Aspect ratio: Output aspect ratio. | auto |
auto |
No |
generate_audio |
Generate audio: Generate native audio with the video. | false |
false |
No |
n |
Outputs per request: Number of outputs from one API request (one Job), not the application batch size. For multiple Jobs, submit separate requests; n=1 does not prevent application-managed batching. | 1 |
1 |
No |
Examples
reference input:
{
"model": "higgsfield/genjutsu-1.0-motion-transfer",
"input": {
"type": "reference",
"prompt": "A paper boat drifting down a rainy city street, slow tracking shot",
"references": [
{
"role": "reference_image",
"file_id": "file_..."
},
{
"role": "reference_video",
"file_id": "file_..."
}
]
},
"parameters": {
"duration": 5,
"resolution": "720p",
"aspect_ratio": "auto",
"generate_audio": false,
"n": 1
}
}
The authoritative contract is GET /v1/models/higgsfield/genjutsu-1.0-motion-transfer?view=contract. A valid parameter does not mean every channel can run it, so quote the complete request. Prices and channels are listed in Model Market.
Source video and billing
Genjutsu transfers motion from one source video to the people in 1–10 reference images. Upload a 1–30 second MP4 using Files.
To replace an object in the source video, choose Genjutsu Object Swap or Genjutsu Light Object Swap. See the Genjutsu request examples.
The output duration and aspect ratio follow the source video. duration is a catalog representative value; it is not sent to the model and does not trim the video. Audio cannot be controlled: generate_audio: true is rejected, while false does not guarantee a silent result. Check the delivered file for an audio track.
Quotes use the longer of the measured audio and video tracks, rounded to the nearest second with a four-second minimum. Reference media have no additional fee. A URL that has not yet been imported has no complete quote; use a newly uploaded, measured file for an estimate. Final charges use the actual task cost.
Compatible request names
Submit and quote requests also accept genjutsu-1.0, nanoapi/genjutsu-1.0.