HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

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

Implementing FlowEdit, maybe other inversion techniques for the Wan video generation model

[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting

Official codes of VEnhancer: Generative Space-Time Enhancement for Video Generation

Everything-Reactivity in ComfyUI (audio, MIDI, motion, proximity, and more). Animate and manipulate images, masks, videos, audio, and more. Native ACEStep extensions

An All-in-One FluxDev workflow in ComfyUI that combines various techniques for generating images with the FluxDev model, including img-to-img and text-to-img. This workflow can use LoRAs, ControlNe…

ComfyUI nodes to use segment-anything-2

ControlNet++: All-in-one ControlNet for image generations and editing!

[ICLR 2025] Official implementation of MotionClone: Training-Free Motion Cloning for Controllable Video Generation

ComfyUI docker images for use in GPU cloud and local environments. Includes AI-Dock base for authentication and improved user experience.

Scaled Uniform Noise for Ancestral & Stochastic samplers and Noisy latent image

ComfyUI TCD implementation

ControlNet scheduling and masking nodes with sliding context support

Improved AnimateDiff for ComfyUI and Advanced Sampling Support

Various custom nodes for ComfyUI

In order to make it easier to use the ComfyUI, I have made some optimizations and integrations to some commonly used nodes.

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

Industry leading face manipulation platform

Helper for automating upload emoji to slack by using puppeteer