[NeurIPS 2025] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance

An extendable generative media application using ImGui, opencv and ggml libraries.

[ArXiv 25] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling

qwen-image and wan2.2 wan2.1 bridge

ComfyUI workflow Sora 2 alike

[SIGGRAPH Asia 2025] DreamO: A Unified Framework for Image Customization

Pip / uv installable ComfyUI package

Repo containing mkdocs md for comfydock.com

a CLI utility/library for AnimateDiff stable diffusion generation

A random assortment of custom ComfyUI nodes

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

A Python frontend and library for ComfyUI

A pipeline parallel training script for diffusion models.

Community trainer for Lightricks' LTX Video model 🎬 ⚡️

Search an index of videos by motion image

Open-Sora: Democratizing Efficient Video Production for All

A CLI tool to help manage ComfyUI environments

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.

The ultimate training toolkit for finetuning diffusion models

A set of nodes to edit videos using the Hunyuan Video model

Flux Fill 1.0 GO: flux Inpainting and outpainting starting with 8Gb of VRAM