Seedance 2.5 Video
vellria-seedance-2-5-videoA cinematic video model. Long scenes and natural camera movement.
Input
Form0 / 10000
Settings
Output
No generation yetCover art
from 28 credits / s
Your request will cost 140 credits.
Your prompt renders as written; a narrow safety filter refuses prohibited content. Content policy
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 route you take in, 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.
Catalog
| Resolution | Credits |
|---|---|
| 480p | 28 credits / s |
| 720p | 60 credits / s |
| 1080p | 120 credits / s |
- Duration
- 4–30s
Variants in this family
What you already have decides it. With only a description, the text variant invents the whole shot from your wording alone. The image variant starts from a picture you supply, takes it as the opening frame and spends the render on movement instead. Neither offers a frame shape to pick, so crop before you upload and let the prompt carry the framing you want.
| Variant | What it does | Credits |
|---|---|---|
| Seedance 2.5 Image Video | Takes the image you provide as the first frame and animates it into a long scene. | from 28 credits / s |