Stars
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
Official inference repo for FLUX.1 models
The ultimate training toolkit for finetuning diffusion models
Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.
Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.
[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
[NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Surpasses GPT-4o in ID persistence~ MoE ckpt released! Only 4GB VRAM is enough to run!
Official SeedVR2 Video Upscaler for ComfyUI
Official inference repo for FLUX.2 models
Qwen-Image-Lightning: Speed up Qwen-Image model with distillation
Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling
Official implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models"
Repo for SeedVR2 & SeedVR (CVPR2025 Highlight)
Training-free Regional Prompting for Diffusion Transformers 🔥
On-device Image Generation for Apple Silicon
[🚀ICML 2025] "Taming Rectified Flow for Inversion and Editing" Using FLUX and HunyuanVideo for image and video editing!
[CVPR 2025] Diffusion Self-Distillation for Zero-Shot Customized Image Generation
An implementation of the CSM(Conversation Speech Model) for Apple Silicon using MLX.
🚀 Cross attention map tools for huggingface/diffusers
Taming large-scale full-parameter few-step training with self-adversarial flows! 👏🏻