ComfyUI nodes to use segment-anything-2

Wrapper node to use Geowizard in ComfyUI

[ECCV'24] GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image

[AAAI 2025] EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

[CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation

Open and efficient video watermarking

State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!

High quality training free inpaint for every stable diffusion model.

A TTS model capable of generating ultra-realistic dialogue in one pass.

A lightweight version of Milvus

A simple, easy-to-hack Vector Database

"VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos"

"MiniRAG: Making RAG Simpler with Small and Free Language Models"

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

GGUF Quantization support for native ComfyUI models

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

SkyReels-A2: Compose anything in video diffusion transformers

VisualCloze: A universal image generation framework that can support a wide range of in-domain tasks and generalize to unseen ones.

StyleShot: A SnapShot on Any Style. 一款可以迁移任意风格到任意内容的模型，无需针对图片微调，即能生成高质量的个性风格化图片!

VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation

[CVPR 2025] UniK3D: Universal Camera Monocular 3D Estimation

Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging

TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models

Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.

Run Orpheus 3B Locally With LM Studio

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

[SIGGRAPH Asia 2024 (Journal Track)] StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal

Unlock Pose Diversity: Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait