SeeDance 2.5 Released: 30s Generation & Multimodal References
Dr_Singularity · x · 2026-08-01
SeeDance has been updated to version 2.5. The new model supports 30-second single-generation videos with multi-round extension capabilities. Additionally, it can accept a wide range of multimodal references during generation, including up to 30 images, 10 videos, and 10 audio clips.
Related event: Seedance 2.5 Released: Native Long Video and Multimodal References(53 posts)→
More from Multimodal
- Seedance 2.0 in Action: Lighting and Camera Moves Hit Cinematic Levels — FellMentKE · 2026-08-01
- MiniMax H3 Hits Topview: Native 2K Video at 30% of Seedance 2.0 Cost — azed_ai · 2026-08-01
- AI Video Workflow Breakdown: Crafting Consistent Multi-Character Shorts — LudovicCreator · 2026-08-01
- Seeking Local ComfyUI Workflows for Google Earth-style Satellite Zoom-ins — justlooking___1 · 2026-08-01
- 7 Practical Ways to Use Gemini Omni for Video Generation and Editing — CodeByPoonam · 2026-08-01
- FLUX 3 Model Test: Generating the Mini-Doc 'Gerald' — heresalexandria · 2026-08-01