Robust Speech Recognition via Large-Scale Weak Supervision

Layer Diffuse custom nodes

TripoSR, a state-of-the-art open-source model for fast feedforward 3D reconstruction

LoRA and DoRA from Scratch Implementations

TripoSR custom node for comfyui

(CVPR 2024) Rethinking Inductive Biases for Surface Normal Estimation

Nodes for using ComfyUI as a backend for external tools. Send and receive images directly without filesystem upload/download.

[WIP] Layer Diffusion for WebUI (via Forge)

Deforum ComfyUI Nodes - ai animation node package

ChatMusician: Fostering Intrinsic Musical Abilities Into LLM

Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation" and "VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation"

Famous Vision Language Models and Their Architectures

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

ComfyUI nodes to use InstanceDiffusion.

Official Repository of the paper "Trajectory Consistency Distillation"

These custom nodes provide a rotation aware face extraction, paste back, and various face related masking options.

Safe FFmpeg wrapper.

GeneFace++: Generalized and Stable Real-Time 3D Talking Face Generation; Official Code

Implementation of MeshGPT, SOTA Mesh generation using Attention, in Pytorch

A ComfyUI custom node that simply integrates the [animate-anyone-reproduction](https://github.com/bendanzzc/AnimateAnyone-reproduction) functionality.

FaceXlib aims at providing ready-to-use face-related functions based on current STOA open-source methods.

Official Code for "SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation"

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

[CVPR 2024] Code for SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes

ComfyUI node pack by cerspense

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

Extension for ComfyUI to evaluate the similarity between two faces

TouchDesigner implementation for Depth Anything and TensorRT monocular depth estimation.

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild