Pose Extraction & Rendering for SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations

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

One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer

comfyui intergration for LongCat-Image

视频号、小程序、抖音、快手、小红书、直播流、m3u8、酷狗、QQ音乐等常见网络资源下载!

[ArXiv 25] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling

MoCha: End-to-End Video Character Replacement without Structural Guidance

Official Implementations for Paper - HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives

Lynx: Towards High-Fidelity Personalized Video Generation

to server only

HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

Voyager is an interactive RGBD video generation model conditioned on camera input, and supports real-time 3D reconstruction.

Stand-In is a lightweight, plug-and-play framework for identity-preserving video generation.

This custom_node for ComfyUI adds one-click "Virtual VRAM" for any UNet and CLIP loader as well MultiGPU integration in WanVideoWrapper, managing the offload/Block Swap of layers to DRAM *or* VRAM …

Some Comfyui custom nodes for wan2.1 VACE, attempt to implement VACE video generation/editing in a better way.

[SIGGRAPH Asia 2024] Painting process generating using diffusion models

Understand Human Behavior to Align True Needs

Official implementation of MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement

Official project page of MTVCrafter, a new paradigm for animating arbitrary characters with 4D motion tokens.

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

Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment

🔥 Motion Anything: Any to Motion Generation

[SIGGRAPH2025] Official repo for paper "Any-length Video Inpainting and Editing with Plug-and-Play Context Control"

[ICCV2025] LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds

🚀 Truly open-source AI avatar(digital human) toolkit for offline video generation and digital human cloning.

This node provides lip-sync capabilities in ComfyUI using ByteDance's LatentSync model. It allows you to synchronize video lips with audio input.