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's Haidian district, with an associated variable-interest entity incorporated in the Cayman Islands. Best known as a consumer internet operator at enormous scale, it has also become a…

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.