Seedance 2.0
Seedance 2.0 is the most flexible video generator in DayGen when you have more than a text prompt. Use it for first/last frames, reference images, short reference videos, audio cues, and structured multimodal direction.
Best for
- multimodal briefs
- first/last frames
- reference videos
- audio-guided video
Use when
- You have a precise start or end frame.
- The prompt needs image, video, and audio references to guide the output.
- You want strong control for product, character, or scene video concepts.
- You are generating a polished create or reference-conditioned edit.
Avoid when
- You only need the fastest rough motion test; use Seedance Fast or P-Video.
- You need text-only cinematic audio from Google; compare Veo 3.1.
Inputs
- prompt
- frames
- image references
Outputs
- video
DayGen surfaces
- /video/create
- /video/edit
- Make Video
- Agent video generation
Available settings
- Mode
- Frames, References
- Aspect Ratio
- Adaptive, 16:9 (Wide), 9:16 (Story), 1:1 (Square), 4:3 (Classic), 3:4 (Portrait), 21:9 (Cinema). The model chooses one fixed output shape from your prompt, frames, and references. The result is not responsive.
- Resolution
- 480p (Faster), 720p (Higher Quality), 1080p (High), 4K (10-bit HEVC)
- Duration
- Auto, 4–15s
- Audio
- Native audio, Up to 3 audio references
- Batch Size
- 1–4