Stars
Official Implementation of SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning
An enhanced tool for CodexApp, striving to make Codex better to use and more comfortable 一个CodexApp的增强工具，努力让Codex变得更好用更舒服
Create and share 3D architectural projects.
PainterFLF2V boosts first-last frame motion with inverse structural repulsion. PainterFLF2V: Dynamically enhances the original first-last frame node, allowing you to customize the dynamic enhanceme…
通过“影子加载”技术实现工作流的秒级启动，并通过“显存排队”机制和模型卸载防止大模型采样时爆显存。
High quality training free inpaint for every stable diffusion model. Supports ComfyUI
Nodes for high resolution outputs and high frame numbers using LTX-2 in ComfyUI
获取微信4.0版本以上数据库密钥和图片密钥的工具 | A tool for obtaining database keys and image keys for WeChat versions 4.0 and above
原 [chatlog]项目（一个微信数据库解密读取及提供mcp服务、http服务的开源软件），现已支持通过微信clawbot接口推送消息，可以实时转发全部或指定消息到clawbot
Node-based video editing template
A highly optimized ComfyUI wrapper for **DreamID-V**, bringing robust identity-preserving video generation to ComfyUI. This implementation focuses on memory efficiency, speed, and seamless integrat…
Professional Antigravity Account Manager & Switcher. One-click seamless account switching for Antigravity Tools. Built with Tauri v2 + React (Rust).专业的 Antigravity 账号管理与切换工具。为 Antigravity 提供一键无缝账号切…
从URL加载视频/音频/图像，支持多媒体合并与音频处理 | ComfyUI nodes for loading video/audio/image from URL with media merging support
Fixes TurboDiffusion lazy loader and vendored import issues in ComfyUI. 修复 TurboDiffusion 在 ComfyUI 中的 LazyModelLoader 参数传递与 vendored 导入路径问题，避免加载错误并保持官方行为一致。
Effortlessly manage your Antigravity multi-accounts
A ComfyUI custom node package for [SAM3 (Segment Anything Model 3)](https://github.com/facebookresearch/sam3), providing powerful image and video segmentation capabilities with text prompts.
A new SOTA for RAG — an original retrieval architecture and an open-source knowledge base for humans and agents.
Pre-compiled Python whl for Flash-attention, SageAttention, NATTEN, xFormer etc
LoRA Loader & Diffsynth ControlNet Loader for Nunchaku Qwen Image & Nunchaku Z-Image Turbo
Comfyui视频动态字幕节点，多种动态效果选择，字体颜色设置，渐变色设置。
[ICLR 26 Oral] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling
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 …