Higgsfield Genjutsu
Motion transfer rebuilds the scene from your photos — a character, a place, a style — and keeps the original motion, camera and timing.
Good for: dances, replacing a person in a clip, and restyling a video
You pay per second of your video. The result is the same length: 4 to 30 seconds; longer clips are trimmed to 30.
For developers →How to get a better result
"A ginger cat on a windowsill, rain outside, watercolor".
"Soft sunset", "neon light", "cozy, warm tones".
Refine the description and press "Another version" — every result is new.
Pass this model in the request higgsfield-genjutsu
1. Create a task POST /api/v1/jobs/createTask
curl -X POST https://mixmedia.tech/api/v1/jobs/createTask \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: order-123" \
-d '{
"model": "higgsfield-genjutsu",
"callBackUrl": "https://your-app.example/callback",
"input": {
"mode": "motion-transfer",
"prompt": "Keep the face from the photo and copy the dance from the video",
"image_urls": [],
"resolution": "720p"
}
}'import time, requests
API = "https://mixmedia.tech/api/v1"
HEADERS = {"Authorization": "Bearer YOUR_API_KEY"}
task = requests.post(f"{API}/jobs/createTask", headers=HEADERS, json={
"model": "higgsfield-genjutsu",
"callBackUrl": "https://your-app.example/callback",
"input": {
"mode": "motion-transfer",
"prompt": "Keep the face from the photo and copy the dance from the video",
"image_urls": [],
"resolution": "720p"
}
}).json()
task_id = task["data"]["taskId"]
while True:
info = requests.get(f"{API}/jobs/recordInfo", headers=HEADERS, params={"taskId": task_id}).json()["data"]
if info["state"] in ("success", "fail"):
break
time.sleep(4)
print(info["state"], info.get("resultJson") or info.get("failMsg"))const API = "https://mixmedia.tech/api/v1";
const headers = { Authorization: "Bearer YOUR_API_KEY", "Content-Type": "application/json" };
const { data } = await fetch(`${API}/jobs/createTask`, {
method: "POST", headers,
body: JSON.stringify({
"model": "higgsfield-genjutsu",
"callBackUrl": "https://your-app.example/callback",
"input": {
"mode": "motion-transfer",
"prompt": "Keep the face from the photo and copy the dance from the video",
"image_urls": [],
"resolution": "720p"
}
}),
}).then((r) => r.json());
let info;
do {
await new Promise((r) => setTimeout(r, 4000));
info = (await fetch(`${API}/jobs/recordInfo?taskId=${data.taskId}`, { headers }).then((r) => r.json())).data;
} while (!["success", "fail"].includes(info.state));
console.log(info.state, info.resultJson ?? info.failMsg);Response: data.taskId. callBackUrl and Idempotency-Key are optional.
2. Status and result GET /api/v1/jobs/recordInfo
curl "https://mixmedia.tech/api/v1/jobs/recordInfo?taskId=TASK_ID" \
-H "Authorization: Bearer YOUR_API_KEY"
data.state: waiting, queuing, generating, success, fail. On success data.resultJson is a JSON string with resultUrls.
3. Upload a file POST /api/v1/files/upload
curl -X POST https://mixmedia.tech/api/v1/files/upload \
-H "Authorization: Bearer YOUR_API_KEY" -F "file=@photo.jpg"
The response has data.url. Pass that URL in the file field. Any public https URL works too.
About the model
Higgsfield Genjutsu takes a finished clip and changes the reality in it without reshooting the motion.
Motion transfer builds a new scene from your photos — a character, a place, a style — and keeps the original motion, camera and timing.
Object swap changes a chosen person, outfit, product or object. The rest of the shot stays as filmed.
Restyle applies a chosen visual style and keeps the clip’s motion and original audio. Photos are optional: without them the style is applied to whoever is already in the frame.
The video is at least 4 seconds; longer than 30 seconds is trimmed to 30. Resolution is 480p, 720p or 1080p. The prompt is optional. Every mode costs the same, per second of your clip.


