Lists (2)
Stars
A geometry-shader-based, global CUDA sorted high-performance 3D Gaussian Splatting rasterizer. Can achieve a 5-10x speedup in rendering compared to the vanialla diff-gaussian-rasterization.
[Official Code] Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction
DCM: Dual-Expert Consistency Model for Efficient and High-Quality Video Generation
UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation
Render human motion sequences with Blender, with or without overlaying on a video
Official Repo for MoCha Towards Movie-Grade Talking Character Synthesis
North Star is a VR showcase for Unity, demonstrating cutting-edge graphics and immersive gameplay on Meta Quest devices. Join a crew of pirates on a quest for mythic treasure, and uncover the secre…
Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets
DFloat11: Lossless LLM Compression for Efficient GPU Inference
ACE-Step: A Step Towards Music Generation Foundation Model
colinurbs / FramePack-Studio
Forked from lllyasviel/FramePackExpanding FramePack into a multifunction video creation tool
A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.
AllTalk is based on the Coqui TTS engine, similar to the Coqui_tts extension for Text generation webUI, however supports a variety of advanced features, such as a settings page, low VRAM support, D…
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation
Codebase for Berkeley Humanoid Lite
Easily download and archive content from Civitai
[AAAI 2025] Event-Enhanced Blurry Video Super-Resolution
[NeurIPS D&B Track 2024] Official implementation of HumanVid
[CVPR 2025] Science-T2I: Addressing Scientific Illusions in Image Synthesis
Implementation for Describe Anything: Detailed Localized Image and Video Captioning
SkyReels-V2: Infinite-length Film Generative model
For unloading a model or all models, using the memory management that is already present in ComfyUI. Copied from https://github.com/willblaschko/ComfyUI-Unload-Models but without the unnecessary ex…