Model-as-a-Service in the making: bring accessible AI to all.
50
Public repositories
94,085
Total stars
6,110
Followers
ModelScope is an organization on GitHub focusing on making AI accessible through various repositories. It primarily uses Python, Jupyter Notebook, and other languages to develop notable projects such as FunASR, ms-swift, and DiffSynth-Studio, which cater to diverse AI applications.
Top languages
Public repositories
FunASR
Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.
ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).
DiffSynth-Studio
Enjoy the magic of Diffusion models!
facechain
FaceChain is a deep-learning toolchain for generating your Digital-Twin.
modelscope
ModelScope: bring the notion of Model-as-a-Service to life.
FunClip
Open-source, accurate and easy-to-use video speech recognition & clipping tool. LLM-based AI clipping integrated.
ms-agent
MS-Agent: a lightweight framework to empower agentic execution of complex tasks
ClearerVoice-Studio
An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.
3D-Speaker
A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization
evalscope
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
AgentEvolver
AgentEvolver: Towards Efficient Self-Evolving Agent System
modelscope-classroom
No description provided for this repository.
sirchmunk
🐿️ Sirchmunk: Raw data to self-evolving intelligence, real-time.
scepter
SCEPTER is an open-source framework used for training, fine-tuning, and inference with generative models.
KAN-TTS
KAN-TTS is a speech-synthesis training framework, please try the demos we have posted at https://modelscope.cn/models?page=1&tasks=text-to-speech
richdreamer
[CVPR2024 (Highlight)] RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D. Live Demo：https://modelscope.cn/studios/Damo_XR_Lab/3D_AIGC
AdaSeq
AdaSeq: An All-in-One Library for Developing State-of-the-Art Sequence Understanding Models
FunCodec
FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music generation et.al.
awesome-deep-reasoning
Collect every awesome work about r1!
DiffSynth-Engine
No description provided for this repository.
easydistill
a toolkit on knowledge distillation for large language models
motionagent
MotionAgent is your AI assistent to convert ideas into motion pictures.
Nexus-Gen
No description provided for this repository.
dash-infer
DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including CUDA, x86 and ARMv9.
MCPBench
The evaluation benchmark on MCP servers
twinkle
Twinkle✨: Training workbench to make your model glow.
AgentJet
Cutting-edge platform for LLM agent tuning. Deliver RL tuning with flexibility, reliability, speed, multi-agent optimization and realtime community benchmarking.
kws-training-suite
No description provided for this repository.
ultron
Ultron: Collective Intelligence System — Shared Memories, Skills, and Harnesses Across Every Agent
modelscope-studio
A third-party component library based on Gradio. Integrates Ant Design, Ant Design X, Monaco Editor and more advanced components to help you build applications efficiently.
normal-depth-diffusion
No description provided for this repository.
lite-sora
An initiative to replicate Sora
mcore-bridge
MCore-Bridge: Providing Megatron-Core model definitions for state-of-the-art large models and making Megatron training as simple as Transformers — with support for 300+ large language models (Qwen3-Next, GLM-5.1, Deepseek-V4, MiniMax-2.7, ...) and 200+ multimodal large models (Qwen3.5, Qwen3-Omni, Gemma4, ...).
flowra
No description provided for this repository.
ms-enclave
A modular and stable agent sandbox runtime environment.
ImagePulse
Open Image Curation Tools
PromptScope
Enjoy easier conversations with LLM
mcp-central
Collection of model-centric MCP servers
Katz
[ATC'25] Katz is a high-performance serving system designed specifically for diffusion model workflows with multiple adapters.
modelscope-mcp-server
ModelScope's official MCP Server (in active development).
sirchmunk-web
The source code for: https://modelscope.github.io/sirchmunk-web/
r-chain
No description provided for this repository.
Trinity-Studio
No description provided for this repository.
langchain-modelscope
Langchain integration for ModelScope
Awesome-Vibe-Research
面向 AI 辅助科研的开放共建仓库 收集和沉淀科研全流程中的 agents、skills、workflows、tools 与最佳实践
modelscope_hub
The official Python client to connect with ModelScope Hub.
comfyscope
Collection of various Comfy components.
twinkle-web
The github website for twinkle-kit
modelscope-skills
Equip your agents with skills to interact with ModelScope
diffusion-templates-web
No description provided for this repository.
Frequently asked questions
What does modelscope build on GitHub?
ModelScope builds a variety of AI tools and frameworks on GitHub, including industrial-grade speech recognition and deep learning toolchains. Key repositories include FunASR and FaceChain, showcasing their commitment to advancing AI technologies.
Which programming languages does modelscope use?
ModelScope primarily uses Python and Jupyter Notebook in their development. Other languages such as HTML, C, JavaScript, and CSS are also utilized, reflecting a diverse technological approach in their projects.
Are modelscope's repositories public?
Yes, all of ModelScope's repositories are public. This openness allows developers and researchers to access and contribute to various projects, promoting collaboration and innovation in the AI space.
Is this exposure intended?
Monitor ModelScope with RepoGuard and get alerted the moment a new public repository appears.
Monitor this account