Stars
COA Tools is a 2D Animation Suite for blender. It offers a 2D cutout animation workflow similar to programs like spine or spriter.
An experiment in using 3D pixel art in Godot 4.2
FastVideo is an open-source framework for accelerating large video diffusion model.
[arXiv 2024] Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis
Generate Diffuse Textures on Meshes with Stable Diffusion.
From anything to mesh like human artists. Official impl. of "MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization"
MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
A set of ComfyUI nodes providing additional control for the LTX Video model
An Open-Source Python3 tool with SMALL models for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowe…
(SIGGRAPH 2024) Portrait3D: Text-Guided High-Quality 3D Portrait Generation Using Pyramid Representation and GANs Prior
A python program that turns an LLM, running on Ollama, into an automated researcher, which will with a single query determine focus areas to investigate, do websearches and scrape content from vari…
Simulate mouse input using hand tracking
a webcam-based virtual gesture mouse that is easy to use with hands on the desk.
MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers
Offical codes for "AutoVFX: Physically Realistic Video Editing from Natural Language Instructions."
The official code for BSTRO in paper: Capturing and Inferring Dense Full-Body Human-Scene Contact, CVPR2022
Lightweight Python framework that provides a high-level API for creating and rendering scenes with Blender.
[CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation
🔥 2D and 3D Face alignment library build using pytorch
Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x faster on consumer devices.
[SIGGRAPH Asia 2024 (Journal Track)] StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal
Code of Pyramidal Flow Matching for Efficient Video Generative Modeling
Official code release for the paper "SkillMimic: Learning Reusable Basketball Skills from Demonstrations"