-
20:29
- 1h ahead
Highlights
- Pro
Stars
A pipeline parallel training script for diffusion models.
YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open
Mirror of the official PostgreSQL GIT repository. Note that this is just a *mirror* - we don't work with pull requests on github. To contribute, please see https://wiki.postgresql.org/wiki/Submitti…
A self hosted virtual browser that runs in docker and uses WebRTC.
Official implementation of "VideoLifter: Lifting Videos to 3D with Fast Hierarchical Stereo Alignment"
💪 [ARXIV 2025] Pytorch implementation of 'HAC++: Towards 100X Compression of 3D Gaussian Splatting'
Official implementation of Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction
jq for binary formats - tool, language and decoders for working with binary and text formats
Provides a radial menu control
Script-IDE is a plugin for Godot. It transforms the Script UI into an IDE like UI. Tabs are used for navigating between scripts. The default Outline got an overhaul and now shows all members of the…
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
Inefficient sample code for getting screen contents in Unity on Meta Quest to workaround lack of 'camera access'
🔥 Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
Detail-Oriented Pixelization based on Contrast-Aware Outline Expansion.
Automagically reverse-engineer REST APIs via capturing traffic
Scalable, fast, and disk-friendly vector search in Postgres, the successor of pgvecto.rs.
Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/
[ICLR2025] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
NobodyWho is a plugin for the Godot game engine that lets you interact with local LLMs.
3D-Graphics-Rendering-Cookbook, Second Edition
[NeurIPS'2024] Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set
Addon to deform 3D meshes using customizable deformers at run-time.
revisiting a known normal transformation in computer graphics
We present StableAnimator, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-quality videos without any post-processing, conditioned on a reference image and a se…