The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

A high-throughput and memory-efficient inference and serving engine for LLMs

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

Wan: Open and Advanced Large-Scale Video Generative Models

Enjoy the magic of Diffusion models!

Official repository for LTX-Video

PersonaPlex code.

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.

Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

Native and Compact Structured Latents for 3D Generation

3D plotting and mesh analysis through a streamlined interface for the Visualization Toolkit (VTK)

A TTS that fits in your CPU (and pocket)

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

LTX-Video Support for ComfyUI

"Effective Whole-body Pose Estimation with Two-stages Distillation" (ICCV 2023, CV4Metaverse Workshop)

Extended pickling support for Python objects

Official inference repo for FLUX.2 models

WFB-NG - the next generation of long-range packet radio link based on raw WiFi radio

Repo for SeedVR2 (ICLR2026) & SeedVR (CVPR2025 Highlight)

Offical Implementation of SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations

Code for the ShapeR research paper

[ICCV 2025] Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models

3-D Scientific Visualization in the Jupyter Notebook

MPFB2 is a free and open source human generator for Blender

Train and block edit and save LoRAs directly inside ComfyUI for Z-image, Flux Klein, SDXL, Flux, WAN 2.2, SD 1.5

RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards.

VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control