Starred repositories
A ComfyUI node that generates a VACE control video and mask for a smooth transition between two videos.
Avernus API server and client for LLM, SDXL, FLUX, Qwen-Image, WAN, and Ace-Step inference and many other architectures.
Transform your Blender scenes into stunning AI-rendered images
Blender plugin for creating walking animations using machine learning 🤖🦿⚙️🦿
An automated pipeline that generates 3D models from 2D images using TripoSR and optimizes them using Blender.
HDRI editor with real-time 3D painting for Blender
[ArXiv 25] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling
HY-Motion model for 3D character animation generation.
Web Based Video Editor Using MLT Framework, Bachelor thesis
A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.
Demo implementation of MoCha Towards Movie-Grade Talking Character Synthesis
Official code for StoryMem: Multi-shot Long Video Storytelling with Memory
Awesome curated collection of images and prompts generated by z-image-turbo state-of-the-art open-source image generation and editing model.
Cross-platform video editing (compositing) software.
A real-time streaming conversational video system that transforms text interactions into continuous, high-fidelity video responses using autoregressive diffusion.
ComfyUI Wrapper for Microsoft Trellis.2 - Native and Compact Structured Latents for 3D Generation
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
High-Quality Text-to-Video Generation with Alpha Channel
Native and Compact Structured Latents for 3D Generation
Blender addon for aligning an object (e.g. a sun) to match the brightest part in a HDRI environment
Repository with diffusers recipes by model
This workflow uses Wan VACE (Wan 2.2 Fun VACE or Wan 2.1 VACE, your choice!) to smooth out awkward motion transitions between video clips. If you have noisy frames at the start or end of your clips…
25
Updated Jan 7, 2026
Fun-ASR is an end-to-end speech recognition large model launched by Tongyi Lab.