Get Started
Home
Topics
Search
Library
Topic · 15 recaps

Diffusion Models

Generative models that learn to reverse a noising process. The dominant approach behind modern image, video, and audio synthesis.
Sort
Newest
Video Generative Models as Geometry Learner
Diffusion · Aug 28
Beyond Pixels: From Video Priors to 4D Worlds
Diffusion · Aug 11
JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion
Diffusion · Aug 4
Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing
Diffusion · Aug 3
PhiZero: A World Model Built Around Physical Language
Diffusion · Jul 30
DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation
Diffusion · Jul 29
Meshy T2: Fast Native Mesh Generation with Flow Matching
Diffusion · Jul 28
Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation
Diffusion · Jul 27
Generative World Renderer at the Speed of Play
Diffusion · Jul 21
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing
Diffusion · Jul 21