Seedance 2.0 Enhanced R2V

• 🏢 ByteDance's flagship reference-to-video model, the enhanced-quality tier
• 🆕 Newest entry in the Seedance 2.0 family (June 2026)
• 🎯 Combines text, images, video, and audio references in one generation
• 🧠 References visual composition, camera language, motion rhythm, and sound
• 📚 Can follow text-based storyboards
• 💬 ByteDance reports improved instruction-following and subject consistency
• 🔧 Adds video editing and shot-extension capabilities
• 🎬 Generates native dual-channel audio

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 ByteDance's reference-to-video (R2V) model in the Seedance 2.0 generation, focused on weaving a text prompt together with mixed reference material into a single coherent video. According to ByteDance, the R2V workflow accepts combined input of text, images, videos, and audio, with the model referencing elements such as visual composition, camera language, motion rhythm, and sound characteristics — it can even follow text-based storyboards.

Within its own family, this Enhanced variant is the higher-quality tier alongside the lighter Seedance 2.0 Fast R2V and the base Seedance 2.0 R2V, and it shares the Seedance 2.0 line with Seedance 2.0 Enhanced for text-to-video.

Relative to the prior generation Seedance 1.5 Pro, ByteDance describes Seedance 2.0 as an upgrade, reporting improved instruction-following and subject consistency, new video editing and shot-extension capabilities, and dual-channel audio.

ByteDance describes the Seedance 2.0 line as preserving subject consistency across multi-shot sequences and supporting the mixed-reference workflow noted above. Specifics of the Enhanced tier beyond catalog context were not available in primary sources at the time of writing.