Skip to content
Projektkategorien

Kreativität und Medien · GitHub

Entdecke Werkzeuge für Bilder, Video, Audio, Zeichnungen und 3D.

Nützliche GitHub-Projekte

16,902 Projekte

FrameGen-Manager

XiaoQAQ10086

238Sterne

一键为 RTX 20和30 系显卡部署 DLSS 帧生成工具以及DLSS5(实验性功能)。One-click deployment of the DLSS frame generation tool and DLSS5 (experimental feature) for RTX 20 and 30 series graphics cards.

jsketcher

xibyte

1,754Sterne
jsketcher preview

Parametric 2D and 3D modeler written in pure javascript

  • Geometric Constraint Solver. This is a most crucial component which allows to solve a system of geometric constraints applied to a sketch. See below the list of supported constraints.
  • 2D Sketcher. Allows to design 2d sketches applying geometric constraints. Uses HTML5 canvas for rendering.
1,116Sterne
SoundMind preview

We introduce the Audio Logical Reasoning (ALR) dataset, consisting of 6,446 text-audio annotated samples specifically designed for complex reasoning tasks. Building on this resource, we propose SoundMind, a rule-based reinforcement learning (RL) algorithm tailored to endow audio language models (ALMs) with deep bimodal reasoning abilities.

Podcini

XilinJia

240Sterne

Open source podcast instrument for Android supporting contents from YouTube and YT Music as well as normal podcasts.

DeLive

XimilalaXiang

263Sterne
DeLive preview

System audio capture + multi-provider ASR + local-first AI review workspace. Floating live captions, 12 ASR backends, 60+ languages, AI summary/chat/mindmap, Open API, MCP server, and Agent Skill.

  • System-audio capture — browser video, live streams, meetings, courses, podcasts, or any other playback source
  • Fourteen ASR backends — Soniox, Volcengine, Groq, SiliconFlow, Mistral AI, Deepgram, AssemblyAI, ElevenLabs, Gladia, Cloudflare Workers AI, 60db, OpenAI-compatible local services, local FunASR / SenseVoice, and local whisper.cpp
Kreativität und MedienTypeScriptApache-2.0GitHub

HiVG

ximinng

784Sterne
HiVG preview

Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling

  • Small Model, Frontier Results — 3B parameters that beat 7/7 proprietary models including GPT-5 and Gemini 2.5 on image-to-SVG.
  • Efficient SVG Token Compression — Hierarchical tokenization (Raw SVG → Atomic tokens → Segment tokens) with 2.76x sequence compression.
452Sterne
SVGDreamerV2 preview

[T-PAMI 2025] Official implementation for "SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation" https://arxiv.org/abs/2411.17832

faultSeg

xinwucwp

299Sterne

Using synthetic datasets to train an end-to-end CNN for 3D fault segmentation (We are working on an improved version!)