higgsfield-genjutsu missing from /v1/videos/models: why
higgsfield-genjutsu is in the Sume video catalog only when its provider is configured. It is Motion Transfer: one video_url plus 1-8 images, 480p or 720p.

If higgsfield-genjutsu is missing from your GET /v1/videos/models list, that is expected: Sume lists it only when its provider is configured. The other eleven catalog ids are always listed. Do not hard-code genjutsu in a pipeline without checking the live list.
What genjutsu is
The Video Router doc describes the row as Motion Transfer only.
| Item | Value |
|---|---|
| Inputs | video_url plus 1-8 reference_image_urls |
| Resolutions | 480p, 720p |
| Duration | 4-30 s; equals the input video length, rounded up |
| Not accepted | Text-only generation, aspect_ratio, generate_audio, bitrate_mode, audio references |
| Catalog presence | Only when the provider is configured |
How it differs from other rows
Motion Transfer takes the movement from your source video and applies it to the character in your reference images. The row is chosen explicitly: sume/auto never routes to it. video_url is accepted only by this row, h3-max-recast and gemini-omni-flash-1.1.
Check for it first
Check for it before you submit, and fall back or fail clearly.
import asyncio, os
import httpx
async def main():
headers = {"Authorization": f"Bearer {os.environ['SUME_API_KEY']}"}
async with httpx.AsyncClient(base_url="https://api.sume.com", headers=headers) as c:
r = await c.get("/v1/videos/models")
r.raise_for_status()
ids = {m["id"] for m in r.json()["data"]}
print("genjutsu available:", "higgsfield-genjutsu" in ids)
asyncio.run(main())If it is not there
If it is absent, a submit with that id returns 404 model_not_found. For a person swap in an existing video, h3-max-recast is the always-listed alternative; it replaces people with 1-4 photos instead of transferring motion onto a still.
Sources
Related posts
More in Models
- How long can one AI video request be? Sume duration windows
Duration windows differ by model: 2 to 30 seconds on wan-3.0, 4 to 30 on seedance-2.5, 3 to 10 on Gemini Omni Flash 1.1. Read them from the catalog.
- Clips for a 180-second Short: Wan 3.0, Seedance 2.5, Kling 3, Omni
A 3-minute Short needs 6 to 18 clips depending on the model's maximum duration. See the table, then join them with Timeline 1.0; auto chunking does the rest.
- Choose a Sume video model in five questions
Five questions pick a Sume video model: length, resolution, source media, audio toggle and price. One dated table maps each answer to model ids.
- Ideogram 4.5 1K or 2K? Same list price, so pick by delivery size
On Sume, Ideogram 4.5 takes resolution 1K or 2K, and the documented list price depends on quality, not size. Choose 2K when the file will be viewed large.
Written by Sume