Get Started
Topic · 18 recaps

Diffusion Models

Generative models that learn to reverse a noising process. The dominant approach behind modern image, video, and audio synthesis.
PostsQuestions
Home
Topics
Search
Library
Sort
Newest
Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation
Diffusion · Sep 8
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes
Diffusion · Sep 3 · 7:30
GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling
Diffusion · Aug 29 · 6:36
Video Generative Models as Geometry Learner
Diffusion · Aug 28
Beyond Pixels: From Video Priors to 4D Worlds
Diffusion · Aug 11 · 8:32
JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion
Diffusion · Aug 4 · 8:28
Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing
Diffusion · Aug 3 · 5:59
PhiZero: A World Model Built Around Physical Language
Diffusion · Jul 30 · 6:56
DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation
Diffusion · Jul 29 · 7:16
Meshy T2: Fast Native Mesh Generation with Flow Matching
Diffusion · Jul 28 · 5:42