Stars
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Instant voice cloning by MIT and MyShell. Audio foundation model.
Easily train a good VC model with voice data <= 10 mins!
Python packaging and dependency management made easy
Industry leading face manipulation platform
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
The open source developer platform to build AI agents and models with confidence. Enhance your AI applications with end-to-end tracking, observability, and evaluations, all in one integrated platform.
Prefect is a workflow orchestration framework for building resilient data pipelines in Python.
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
Wan: Open and Advanced Large-Scale Video Generative Models
Wan: Open and Advanced Large-Scale Video Generative Models
This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020. For HD commercial model, please try out Sync Labs
HunyuanVideo: A Systematic Framework For Large Video Generation Model
Open Source framework for voice and multimodal conversational AI
Code for the paper Hybrid Spectrogram and Waveform Source Separation
Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, 20+ clouds, or on-prem).
Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation
Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also …
Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"
[ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning.