标签：扩散模型

OneDiff: An out-of-the-box acceleration library for diffusion models.

[ICLR 2025] CatVTON is a simple and efficient virtual try-on diffusion model with 1) Lightweight Network (899.06M parameters totally), 2) Parameter-Efficient Training (49.57M parameters trainable) and 3) Simplified Inference (< 8G VRAM for 1024X768 resolution).

HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo

[CVPR2024 Highlight] VBench - We Evaluate Video Generation

:metal: TT-NN operator library, and TT-Metalium low level kernel programming model.

[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation

Tracking and collecting papers/projects/others related to Segment Anything.

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

A curated list of Diffusion Model in RL resources (continually updated)

[ACM MM 2025] FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis

[ICLR'24] Official PyTorch Implementation of Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors

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

Official implementation of "MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling"

An open-source project for Windows developers to learn how to add AI with local models and APIs to Windows apps.

We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.

Multimodal RL training framework for diffusion & omni models

High quality training free inpaint for every stable diffusion model. Supports ComfyUI

Timestep Embedding Tells: It's Time to Cache for Video Diffusion 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.

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

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

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

Scalable and memory-optimized training of diffusion models

[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.

Research of DeepSeek Engram Architecture based on Qwen-3 and Stable Diffusion series.

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

Offline inference engine for art, real-time voice conversations, LLM powered chatbots and automated workflows

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

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

HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation

The simplest way to serve AI/ML models in production

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

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

a self-hosted webui for 30+ generative ai

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

NVIDIA FastGen: Fast Generation from Diffusion Models

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

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

🔥 On-Policy Self-Distillation in Diffusion Models

[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

[ECCV 2026] Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

[ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++

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

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

one summary of diffusion-based image processing, including restoration, enhancement, coding, quality assessment

Summary of key papers and blogs about diffusion models to learn about the topic. Detailed list of all published diffusion robotics papers.

MindSpore + 🤗Huggingface: Run any Transformers/Diffusers model on MindSpore with seamless compatibility and acceleration.

Open data and scalable training for long-horizon video world models.

App showcasing multiple real-time diffusion models pipelines with Diffusers