Type a name, or just describe what you need. Results blend keyword and meaning-based search. 30 matches, each with an EU availability status.
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.
Research · ByteDance
ByteDance research method for post-training image diffusion models using on-policy self-distillation from reward signals.
Model · ByteDance
Diffusion-based vision-language model from PKU MSALab and ByteDance that captions multiple image regions in parallel.
Model · Unconventional AI
Proof-of-concept image generator from Unconventional AI that uses coupled oscillators instead of diffusion.
Library
Training-free staged sampling method that speeds up pretrained flow-matching text-to-image diffusion models.
Model
Training-free method that rescales attention across RoPE components to generate ultra-high-resolution images with diffusion transformers.
Model · Nvidia
NVIDIA pixel-diffusion decoder that turns latents into 2K–4K images, replacing VAE decode plus a separate upscaler.
Model · DiffuSpace AI
Open-weights diffusion language model from DiffuSpace AI with 35B total and 3B active parameters.
Pixel-space text-to-image diffusion model transferred from latent diffusion models, without a VAE, supporting 4K output.
Model · Meta
Meta and HKUST research method for fast artist-like 3D mesh generation using a MeshVAE and flow-based diffusion transformer.
Diffusion transformer that generates rigid and elastic 3D mesh dynamics in world coordinates from initial velocities and materials.
Model · InternLM
Multi-codebook diffusion LLM from Shanghai AI Laboratory for visual understanding, image generation and image editing.
Model · Kandinsky Lab
Open-source diffusion models for synchronized 5-second video and audio generation, with a Full HD super-resolution add-on.
Research framework for real-time, causal streaming video editing with diffusion, running at about 12.66 FPS.
ByteDance and Texas A&M research method distilling image and video diffusion models into few-step generators adversarially.
ByteDance research method for few-step diffusion distillation, adding a one-line projection to the DMD update.
Library · Ostris
Open-source GUI and CLI training suite for fine-tuning image and video diffusion models, including LoRAs, on consumer GPUs.
Model · SupraLabs
Tiny 100M-parameter open-weights text-to-image diffusion transformer from SupraLabs, generating 256×256 images.
NVIDIA's 5B and 14B hybrid linear-attention video diffusion transformers generating up to 720p on a single GPU.
Model · Princeton
Fully open 3B text-to-image diffusion model from Princeton with released weights, training code, and data pipeline.
Text-to-image foundation model family (1B, 2B, 5B) using Semantic-First Diffusion with separate semantic and texture streams.
Model · Linum AI
2B-parameter pixel-space text-to-image diffusion model from Linum AI, trained from scratch for about $21K; Apache 2.0.
Library · Tencent
Positional encoding method that gives video diffusion transformers precise camera control from an image and camera path.
