PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion

Official repository of In-Context LoRA for Diffusion Transformers

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

Lightweight Image Video Action Generation Inference Framework

FreeFuse: Multi-Subject LoRA Fusion via Adaptive Token-Level Routing at Test Time

Awesome Knowledge Distillation

Audio Reactivity Nodes for ComfyUI 🔊 Create AI generated audio-driven animations

GLM-Image: Auto-regressive for Dense-knowledge and High-fidelity Image Generation.

🏔️ Mass Image Downloader is a Chromium (MV3) extension that helps you collect and download images at scale—from single pages, multi-page galleries, or across open tabs—while keeping results high-qu…

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

This script merges multiple sharded safetensors files into a single safetensors file.

neosr is an open-source framework for training super-resolution models.

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

🔥 [ICCV 2025 Highlight] Official ComfyUI native node supporting InfiniteYou with FLUX

ComfyUI extension that enables multi-GPU processing locally, remotely and in the cloud

GUI-focused roop

FILM: Frame Interpolation for Large Motion, In ECCV 2022.

Fast and memory-efficient exact attention

Fast and memory-efficient exact attention

[CVPR 2026] 🔥🔥 Official Repo of USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning

SoTA open-source TTS

Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019). A PyTorch implementation.

Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation (ECCV2022)

Official Implementation for "HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing" (CVPR 2022) https://arxiv.org/abs/2111.15666

DifFace: Blind Face Restoration with Diffused Error Contraction (TPAMI, 2024)

This is the official implementation of "The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing"

Dlib compiled binaries (.whl) for Python 3.7-3.14 and Windows x64