Julius Berner
@julberner • 1,353 subscribers
Research scientist @nvidia | postdoc @caltech | PhD @univienna | former research intern @MetaAI and @nvidia | views are my own
Videos
Why choose between autoregressive (fast, streaming) and bidirectional (high-quality) video diffusion when a single model can do both even better? Excited to share Flex-Forcing, accepted as spotlight at #ICML2026! 📍Say hi to Chao Liu at our poster: July 9 | 2:30 - 4:15 PM KST | Hall A #3909 Joint work with Xinyin Ma Weili Nie Arash Vahdat Xinchao Wang
Julius Berner10,443 просмотров • 3 месяцев назад
🚀🎬We introduce TMD (Transition Matching Distillation): 480p videos generated from text prompts in < 3 NFEs! 1️⃣Main backbone for feature extraction and lightweight head for iterative refinement 2️⃣Distilled from Wan2.1 14B T2V combining MeanFlow & DMD2 🔗
Julius Berner17,026 просмотров • 9 месяцев назад
Struggling with slow inference of diffusion and flow models? Check out the video below—I’ve been using our new FastGen library to achieve 7-28x acceleration for text-2-image and {text,image,video}-2-video generation without sacrificing visual fidelity!
Julius Berner13,780 просмотров • 8 месяцев назад
Больше нет контента для загрузки