Seedance 2.0 R2V Enhanced

• 🏢 ByteDance's flagship reference-to-video endpoint in the Seedance 2.0 Enhanced tier
• 🆕 Reference-to-video mode within the Seedance 2.0 line
• 🎯 Combines multiple image, video, and audio references in one generation
• 📏 Generates 15-second multi-shot clips at 720p
• 🔧 Native joint audio-video generation with dual-channel sound
• 👁️ Editing and extension: alter clips while preserving motion, camera
• 💬 Reads text storyboards and shooting scripts to direct composition
• 🌐 Released June 2026; built on a unified multimodal architecture

ByteDance

ByteDance is a Chinese internet technology company headquartered in Beijing, widely known as the parent company behind TikTok and Douyin. Beyond social media, ByteDance has invested heavily in artificial intelligence research, building generative media models…

Seedance 2.0 Enhanced R2V is the reference-to-video ("R2V") endpoint of ByteDance's Seedance 2.0 Enhanced tier, dated June 2026 and the newest entry in the Seedance family. The R2V mode accepts mixed inputs — ByteDance describes combining images, video clips, and audio files in a single generation, referenced in the prompt to drive style transfer, motion transfer, lip-sync, and character consistency. Beyond generation, it handles editing and extension: modifying specified clips, characters, or actions while preserving the original motion and camera work, or continuing a scene with consistent characters and style.

Within the 2.0 line, the Enhanced tier sits alongside the base Seedance 2.0 R2V and the lighter Seedance 2.0 Fast R2V, sharing the 15-second, multi-shot, 720p envelope and native audio-video generation that defines the family.

Against earlier generations, ByteDance describes Seedance 2.0 as a substantial upgrade over Seedance 1.5 Pro, citing improved instruction-following, more stable subject consistency, and better motion and physics for complex interactions like sports, dancing, and collisions. It also adds dual-channel audio and the ability to reference text-based storyboards directly.

It sits within the broader Seed lineup alongside the Seedance 2.0 Enhanced text endpoint and the Seedream V5 Lite image models. Most technical figures here are vendor-reported; consult ByteDance's official Seedance 2.0 documentation for precise parameters.