Seedance
The price-to-quality balance point, and the multimodal one
Seedance is the default recommendation for general video work: it is uncensored, it is the best value per second in the catalogue, and the 2.0 line takes references as *inputs to the prompt* — you pass images, videos and audio and address them in the text as [Image 1], [Video 2]. That is a different way of working from every other family here.
Strengths and limits
Key Features
- Best price-to-quality ratio for everyday video; Pro Fast is the cheapest usable draft in the product.
- Multimodal references on 2.0: drive a generation from several images, a source video and an audio track at once.
- 1.5 Pro produces joint audio and video with micro-expressions, and supports first + last frame.
- Uncensored, with fast variants of every tier so an iteration loop stays cheap.
Where it falls down
- The 2.0 line is capped at 480p and 720p. For 1080p delivery, use 1.5 Pro or the WAN line.
- Fast variants trade prompt understanding for price — a complex instruction may need the full tier.
- Multimodal mode requires a prompt that actually references the inputs; passing references without addressing them wastes them.
Model
Capability tables are read from the live model catalogue. Where a table and a paragraph disagree, the table is right.
| Model | Tools | Quality | Duration | Resolution | Audio | Filters | Credits |
|---|---|---|---|---|---|---|---|
| Seedance 2.5seedance_2_5 | Text-to-Video | BEST OF THE BEST | 5–15s | 480p · 720p | Filters: Minimal | 13 credits | |
| Seedance 2.0seedance_2_0 | Text-to-Video | STANDARD | 5–15s | 480p · 720p | Filters: Minimal | 9 credits | |
| Seedance 2.0 Fastseedance_2_0_fast | Text-to-Video | STANDARD | 5–15s | 480p · 720p | Filters: Minimal | 7 credits | |
| Seedance 2.5 Editseedance_2_5_edit | Video-to-Video | BEST OF THE BEST | 5–15s | 480p · 720p | Filters: Minimal | 7 credits | |
| Seedance 2.0 Fast Editseedance_2_0_fast_sfw | Video-to-Video | QUICK & CHEAP | 5–15s | 480p · 720p | Filters: Minimal | 7 credits | |
| Seedance 2.0 Editseedance_2_0_sfw | Video-to-Video | BEST OF THE BEST | 5–15s | 480p · 720p | Filters: Minimal | 7 credits | |
| Seedance 2.5seedance_2_5 | Image-to-Video | BEST OF THE BEST | 5–15s | 480p · 720p | Filters: Minimal | 13 credits | |
| Seedance 2.0seedance_2_0 | Image-to-Video | BEST OF THE BEST | 5–15s | 480p · 720p | Filters: Minimal | 9 credits | |
| Seedance 2.0 Fastseedance_2_0_fast | Image-to-Video | QUICK & CHEAP | 5–15s | 480p · 720p | Filters: Minimal | 7 credits | |
| Seedance 2.0 Miniseedance_2_0_mini | Image-to-Video | QUICK & CHEAP | 5–15s | 480p · 720p | Filters: On | 5 credits |
Tools
Start from text
Start from an image
Start from a video
Frequently Asked Questions
You attach up to several images, videos and audio clips to one generation, then refer to them in the prompt by index — "[Image 1] walks into the room lit like [Image 2], scored to [Audio 1]". The model composes from those inputs instead of guessing from words alone.