Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones

This repo lists relevant papers summarized in our survey paper: A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models.

③[IQA, IAA, VQA] All-in-one Foundation Model for visual scoring. Can efficiently fine-tune to downstream datasets.

A set of nodes for ComfyUI that generate image like Adobe Photoshop's Layer Style.

StyleAligned for ComfyUI

This custom node lets you train LoRA directly in ComfyUI!

[ICCV 2023] Official implementation of "DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders"

Create bounding boxes selecting masks by threshold.

A set of custom nodes for ComfyUI. The nodes utilize the face parsing model to provide detailed segmantation of face.

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

The source code of "DINet: deformation inpainting network for realistic face visually dubbing on high resolution video."

Official implementations for paper: DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models

ComfyUI wrapper node for CCSR

Using Gemini in ComfyUI

An extensive node suite that enables ComfyUI to process 3D inputs (Mesh & UV Texture, etc) using cutting edge algorithms (3DGS, NeRF, etc.)

Rhubarb Lip Sync is a command-line tool that automatically creates 2D mouth animation from voice recordings. You can use it for characters in computer games, in animated cartoons, or in any other p…

This repository is a custom node in ComfyUI. This is a program that allows you to use Huggingface Diffusers module with ComfyUI. Additionally, Stream Diffusion is also available.

Official implementations for paper: Anydoor: zero-shot object-level image customization

Easily use MagicAnimate within ComfyUI

An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation

DragNUWA enables users to manipulate backgrounds or objects within images directly, and the model seamlessly translates these actions into camera movements or object motions, generating the corresp…

Fine tuned GPT-J model to create rap lyrics that rhyme and incorporate meter

MotionCtrl: A Unified and Flexible Motion Controller for Video Generation

ComfyUI-Openpose-Editor-Plus- provides image overlay pose

A port of the openpose-editor extension for stable-diffusion-webui, now compatible with ComfyUI

Goxel: Free and Open Source 3D Voxel Editor

Code for "Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds"