Seedance 2.5 Uncensored
Generates from a prompt, or animates a reference image, 4 to 30 seconds at 480p to 1080p.
vellria-seedance-2-5Seedance 2.5 is developed by ByteDance. Vellria provides access to the model; it does not own it. All trademarks belong to their respective owners.
Output
No generation yetCover art
from 35 credits / s
Your request will cost 175 credits.
Overview
Sound arrives with the picture in this family, which is the thing to plan around: a take is not a silent clip you score afterwards but a scene that comes back finished, and the audio follows what the prompt describes rather than what you add later. Write the action as one continuous description — a take runs start to finish once it begins, and you steer it by re-running the prompt, not by trimming mid-clip.
Whichever way you start it, the spending decision is made before the clip starts. Resolution sets a rate per second and length multiplies it, so the two compound rather than add, and a long take at the top of the ladder is a different order of cost from the same wording tried short and low. Settle staging and pacing at the shortest length the model accepts and the cheapest step, then re-run what you meant to keep. That re-run is a fresh draw and not an enlargement: the same description, drawn again, and it can land somewhere else.
Prompt or reference
What you already have decides it. With only a description, the model invents the whole shot from your wording alone. Attach a picture and it starts from that instead, taking it as the opening frame and spending the render on movement. Neither mode offers a frame shape to pick, so crop before you upload and let the prompt carry the framing you want.
Specifications
- Resolution: 480p720p1080p
- Duration: 4–30s
- Aspect ratio (Text to video): Auto (chosen from prompt)21:916:94:31:13:49:16
- Reference images: 1–1 reference images
How the video side of the catalog works as a whole, and what it allows, is on the uncensored AI video generator page; explicit clips have their own page on NSFW video generation, and starting from a still is covered under NSFW image to video.
Pricing
| Resolution | Credits |
|---|---|
| 480p | 35 credits / s |
| 720p | 75 credits / s |
| 1080p | 150 credits / s |
Call it from the API
Send vellria-seedance-2-5 as the model field to POST /v1/generate/video, with your API key as a Bearer token. The request below uses this model's default settings from the catalog and returns a generation id to poll.
curl https://vellria.com/v1/generate/video \
-H "Authorization: Bearer vll_..." \
-H "Content-Type: application/json" \
-d '{
"model": "vellria-seedance-2-5",
"prompt": "…",
"duration": 4,
"resolution": "480p",
"ratio": "adaptive"
}'Every parameter, the polling call and the upload endpoint are in the API documentation; every video model id with its price is on the NSFW video API page.