(NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis

[ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation"

[ECCV 2024] MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model.

ControlNet++: All-in-one ControlNet for image generations and editing!

Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025) , UltraViCo (ICLR 2026) and UltraImage

[CVPR 2026] Official Implementation of Free-Lunch Long Video Generation via Layer-Adaptive O.O.D Correction

Anime face landmark detection by deep cascaded regression

Information collection for the Happy Horse AI video generator model. Official demo and updates at happyhorses.io.

The official SpeakerVid-5M data curation code.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

[ACM MM 2025] Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis

[AAAI 2026] EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation

(CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

Official Repo for Self-Forcing++ High Quality Long Video Generation

[CVPR2026]We present FlashPortrait, an end-to-end video diffusion transformer capable of synthesizing ID-preserving, infinite-length videos while achieving up to 6$\times$ acceleration in inference…

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

This is a ComfyUI plugin for https://github.com/Soul-AILab/SoulX-FlashTalk/tree/main

SoulX-FlashTalk is the first 14B model to achieve sub-second start-up latency (0.87s) while maintaining a real-time throughput of 32 FPS on an 8xH800 node.

Comfyui implementation of OpenIXCLab Sec-4B

Qwen-Image-Lightning: Speed up Qwen-Image model with distillation

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

Qwen3.6 is the large language model series developed by Qwen team, Alibaba Group.

GGUF Quantization support for native ComfyUI models

ComfyUI wrapper for segment anything 3