HeyGen launches Avatar 6: 84.4% of frames indistinguishable from real footage
csvoss · x · 2026-11-18
HeyGen launched Avatar 6, its new AI avatar model, with a live demo scheduled for Nov 18, 10am PT. Unlike previous avatars that recycled looping gestures, Avatar 6 reads the script and performs it your way on the first take.
Key claims: native 2K output throughout, and in side-by-side tests with real footage 84.4% of frames are indistinguishable from real humans, up from 44.4% for Avatar V. It adds context-aware gestures (pointing, counting, directional motion matched to the script), fresh varied motion on every line, fine-grained prompting of emotion and expressions. HeyGen is also now available as a ChatGPT plugin.
Related event: HeyGen Launches Avatar 6, Blurring the Line Between Digital and Real Humans(3 posts)→
More from Multimodal
- Selective-color portrait with Gemini 4 Argon: peeled layer revealing vivid eyes — AnswerVinod · 2026-11-18
- Midjourney's Edit Model Now Supports Moodboards, Style Codes and Style References — midjourney · 2026-11-18
- MOSS-Image FP16-fixed weights bring speed boost to aging Turing GPUs — mkrGG · 2026-11-18
- One JSON prompt, three tools: Claude vs ChatGPT vs Figma Make for pixel-perfect UI — Tegadesigns · 2026-11-18
- Kling Motion Control Keeps Importing Reference Image Background Into Generated Videos — Flat-Scholar1878 · 2026-11-18
- Mega Max h3 image test: 8MP output with Witcher character swap at CFG 1 — VasaFromParadise · 2026-11-18