Type a name, or just describe what you need. Results blend keyword and meaning-based search. 15 matches, each with an EU availability status.
Model
Research code that streams video generation chunk by chunk from a rough 3D proxy, built on Code World Model.
Diffusion transformer that generates rigid and elastic 3D mesh dynamics in world coordinates from initial velocities and materials.
Research · ByteDance
ByteDance research method for post-training image diffusion models using on-policy self-distillation from reward signals.
Model · Google
Google's open-weights 26B diffusion language model that drafts blocks of text in parallel.
Model · Amazon
Amazon's looped diffusion language models (1.7B and 8B) with adaptive per-token computation, built on Qwen3.
Model · NVIDIA
NVIDIA autoregressive diffusion model for real-time, text- and constraint-controlled 3D human motion generation.
Library
Training-free staged sampling method that speeds up pretrained flow-matching text-to-image diffusion models.
Research
Diffusion framework that learns text-to-3D human motion generation from 2D poses extracted from monocular videos.
Model · Alibaba
Alibaba's diffusion-transformer model that animates a character image from a driving video, with a real-time Lite variant.
Pixel-space text-to-image diffusion model transferred from latent diffusion models, without a VAE, supporting 4K output.
Research framework for real-time, causal streaming video editing with diffusion, running at about 12.66 FPS.
ByteDance research method for few-step diffusion distillation, adding a one-line projection to the DMD update.
ByteDance and Texas A&M research method distilling image and video diffusion models into few-step generators adversarially.
Model · Princeton
Fully open 3B text-to-image diffusion model from Princeton with released weights, training code, and data pipeline.
One- and two-step image generation model distilled from Z-Image-Turbo using text-stream adversarial distillation.
