ByteDance Launches Seedance 2.5: Supports 50 References and 30s Video Generation
FellMentKE · x · 2026-08-02
ByteDance's AI product Dreamina has globally launched the video generation model Seedance 2.5. The model aims to eliminate the traditional trade-offs creators face between freedom and control, or reference volume and workflow manageability.
Key features include:
- Support for up to 50 multimodal references
- Single-generation video up to 30 seconds
- The lowest-cost access to the Seedance family
Early access is currently live on Dreamina, with US availability expected in about a week.
Related event: ByteDance Releases Seedance 2.5 Video Generation Model(2 posts)→
More from Multimodal
- Midjourney 8.2 Showcase: Retro Film Aesthetics with Light Leaks — michaelrabone · 2026-08-02
- MiniMax H3 Multimodal Generation: Mix Video, Image, Text, and Audio Inputs — piotrbinkowski · 2026-08-02
- Musk Marvels at AI Generating Months-Long Special Effects in Seconds — elonmusk · 2026-08-02
- ByteDance Launches Seedance 2.5: Native 30s Videos & 50 Multimodal References — aftahi_ai · 2026-08-02
- Grok Imagine Introduces Character Consistency for Cohesive Visual Storytelling — XFreeze · 2026-08-02
- AI-Generated Short Film: 'Bambi the Destroyer' Episode 8 — rad_city · 2026-08-02