Awesome Opensource Ai

Align Anything: Training All-modality Model with Feedback

Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

Optimizing inference proxy for LLMs

[AAAI 2025] EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

An open-source model family for long-form speech, dialogue synthesis, voice design, sound effects, and real-time streaming TTS

A library for mechanistic interpretability of GPT-style language models

VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

Generative models for conditional audio generation

The best OSS video generation models, created by Genmo

⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)

Eagle: Frontier Vision-Language Models with Data-Centric Strategies

MTEB: State-of-the-art evaluation of embeddings across languages and modalities

Dead simple FLUX LoRA training UI with LOW VRAM support

Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.

[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

[NeurIPS 2025] OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vision-Language Models (VLMs), capable of generating complex and detailed SVGs, from simple icons to intricate anime characters.

Fully open data curation for reasoning models

Helios: Real Real-Time Long Video Generation Model

[CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents

Reference implementations of MLPerf® training benchmarks

MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with block diffusion, mixed-CoT, unified RL)

[ECCV 2024] PowerPaint, a versatile image inpainting model that supports text-guided object inpainting, object removal, image outpainting and shape-guided object inpainting with only a single model. 一个高质量多功能的图像修补模型，可以同时支持插入物体、移除物体、图像扩展、形状可控的物体生成，只需要一个模型