diffusion-models

Scalable and memory-optimized training of diffusion models

[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching

[ICLR 2023 Oral] Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model

FireRed-Image-Edit is a powerful image editing foundation model achieving open-source state-of-the-art performance with precise instruction following, high-fidelity generation, superior identity consistency, and seamless multi-element fusion.

[AAAI 2025]👔IMAGDressing👔: Interactive Modular Apparel Generation for Virtual Dressing. It enables customizable human image generation with flexible garment, pose, and scene control, ensuring high fidelity and garment consistency for virtual dressing.

[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

📦Portable package for running Hunyuan3D 2.0/2.1 on Windows. | 混元 3D 2.0/2.1 整合包

Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.

[CVPR 2025 Oral & Best Paper Finalist] Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models

[CVPR2024, Highlight] Official code for DragDiffusion

A family of diffusion models for text-to-audio generation.

A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control

HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation

PyTorch implementation of MeanFlow & iMF (one-step generative modeling).

Wunjo CE: Face Swap, Lip Sync, Control Remove Objects & Text & Background, Restyling, Audio Separator, Clone Voice, Video Generation. Open Source, Local & Free.

[ICLR24] Official implementation of the paper “MagicDrive: Street View Generation with Diverse 3D Geometry Control”

A collection of resources on controllable generation with text-to-image diffusion models.

A foundation model that generates synchronized video and audio in a single model

Stable Diffusion implemented from scratch in PyTorch

[ICLR'24 spotlight] Chinese and English Multimodal Large Model Series (Chat and Paint) | 基于CPM基础模型的中英双语多模态大模型系列

[ECCV 2024 Oral] MotionDirector: Motion Customization of Text-to-Video Diffusion Models.

[ICLR 2025 Oral] The official implementation of "Diffusion-Based Planning for Autonomous Driving with Flexible Guidance"

[CVPR 2025 Highlight] 3DTopia-XL: High-Quality 3D PBR Asset Generation via Primitive Diffusion

[ICLR 2024 Spotlight] SyncDreamer: Generating Multiview-consistent Images from a Single-view Image

Official implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models"

NVIDIA FastGen: Fast Generation from Diffusion Models

[CVPR 2024] PIA, your Personalized Image Animator. Animate your images by text prompt, combing with Dreambooth, achieving stunning videos. PIA，你的个性化图像动画生成器，利用文本提示将图像变为奇妙的动画

[CVPR 2024] DeepCache: Accelerating Diffusion Models for Free

Official implementation of Diffusion Autoencoders

[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization