PersonaLive! : Expressive Portrait Image Animation for Live Streaming

Structured Video Comprehension of Real-World Shorts

[CVPR 2025 Highlight🌟] Official ComfyUI implementation of "HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesis"

Kandinsky 5.0: A family of diffusion models for Video & Image generation

A custom node set for Video Frame Interpolation in ComfyUI.

This is a ComfyUI-Windows implementation of the image animation projects -> UniAnimate and Animate-X.

​​Unlimited-length talking video generation​​ that supports image-to-video and video-to-video generation

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers

[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

State-of-the-art 2D and 3D Face Analysis Project

[ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing

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

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.

Examples of ComfyUI workflows

comfyui colabs templates new nodes

[ICCV 2025, Highlight] ZIM: Zero-Shot Image Matting for Anything

Audio visualizer library for javascript. Create dynamic animations that react to an audio file or audio stream.

Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

NanoGPT (124M) in 3 minutes

A MLX port of FLUX and other state of the art diffusion image models based on the Huggingface Diffusers implementation.

[NeurIPS 2025] Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation

Testing baseline LLMs performance across various models

Robust Speech Recognition via Large-Scale Weak Supervision