标签：扩散模型

Unified Codebase for Advanced World Models.

Open-source SOTA multi-image editing model

Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction (ICCV 2025)

[CVPR 2025 Highlight🔥] Identity-Preserving Text-to-Video Generation by Frequency Decomposition

DeepInverse: a PyTorch library for solving imaging inverse problems using deep learning

Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025) , UltraViCo (ICLR 2026) and UltraImage

Refiners (discontinued early 2025) was a microframework on top of PyTorch with first-class citizen APIs for foundation model adaptation.

A curated list of 3D Vision papers relating to Robotics domain in the era of large models i.e. LLMs/VLMs, inspired by awesome-computer-vision, including papers, codes, and related websites

Simple and readable code for training and sampling from diffusion models

Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. ACM Computing Surveys, 2026.

Apply diffusion models using the new Hugging Face diffusers package to synthesize music instead of images.

A collection of awesome video generation studies.

A Minimalist, Batteries-included Repository for Advancing World Model Science.

A collection of awesome text-to-image generation studies.

Open-source local AI SDK - run AI on-device with no cloud, no API keys. Supports GGUF, RAG, image, music, and video generation, speech-to-text, P2P inference, and more. Cross-platform: Linux, macOS, Windows, Android, iOS.

A unified framework for easy fine-tuning in Flow-Matching models

Colab Notebooks covering deep learning tools for biomolecular structure prediction and design

[NeurIPS 2024] Simple and Effective Masked Diffusion Language Model

[ICCV 2025] Official implementation of the paper “MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control”

Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks, including end-to-end large-scale multi-modal pretrain models and diffusion model toolbox. Equipped with high performance and flexibility.

A Curated List of Awesome Video World Models with AR Diffusion: Covering Algorithms, Applications, and Infrastructure, Aimed at Serving as a Comprehensive Resource for Researchers, Practitioners, and Enthusiasts.

Fizgig — LoRA & Fine-tune Studio for Klein 9B, Krea 2, MiniMax H3, Qwen Image 2.1, Anima & Z-Image Turbo and Ace-Step XL: train, fine-tune, profile, repair and extract LoRAs & LoKR for Image, Video & Music Models

[ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"

HunyuanImage-2.1: An Efficient Diffusion Model for High-Resolution (2K) Text-to-Image Generation​

A Collection of Papers and Codes for CVPR2026/CVPR2025/ICCV2025/CVPR2024/ECCV2026/ECCV2024 AIGC

DFloat11 [NeurIPS '25]: Lossless Compression of LLMs and DiTs for Efficient GPU Inference

[IJCV 2026] FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds. AI拟音大师，给你的无声视频添加生动而且同步的音效 😝

Open diffusion language model for code generation — releasing pretraining, evaluation, inference, and checkpoints.

[ICLR 2025] Autoregressive Video Generation without Vector Quantization

OpenMusic: SOTA Text-to-music (TTM) Generation

[CVPR'26 Highlight] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

The open .char format for consistent characters. Face, body, wardrobe & voice in one file, consistent across every model.

Train and block edit and save LoRAs directly inside ComfyUI for Z-image, Flux Klein, SDXL, Flux, WAN 2.2, SD 1.5

Refine and improve the quality of small faces in MiniMax H3 video. Per-frame face tracking, crop, refine with H3, stitch back.

[ICCV 2025 & TPAMI] VistaDream: Sampling multiview consistent images for single-view scene reconstruction

水仙的AI提示词｜5,000+ 中文 AI 绘画提示词库：检索 / 分类 / 一键复制。提示词覆盖 ChatGPT、Grok、Gemini、Midjourney、Stable Diffusion、Flux、即梦、可灵、豆包、海螺、文心一格等主流生图模型。源码 + 数据集全部开源。

One-click Portable Windows installation of 'AI-Toolkit by Ostris'

Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform

本地优先的全栈 AI 创作工作站：AI对话 · AI漫画 · 漫剧创作 · 写作台 · 知识学习五大模块；vLLM / llama.cpp / Transformers 多引擎本地推理，显存智能调度、舱壁隔离自愈、仅供学习使用，欢迎交流指正。（最新进度（除插件系统）受到协议限制，暂时无法提交到仓库）

[NeurIPS 2024] SCube: Instant Large-Scale Scene Reconstruction using VoxSplats

RESTai is an AIaaS (AI as a Service) open-source platform. Supports many public and local LLM suported by Ollama/vLLM/etc. Precise embeddings usage, tuning, analytics etc. Built-in image/audio generation with dynamic loading generators. Live chat deployment. Built-in block based graphical language. Prompt versioning and much more...

Papers and resources on Controllable Generation using Diffusion Models, including ControlNet, DreamBooth, IP-Adapter.

Official implementation of AsymFlow, pi-Flow, GMFlow

A curated archive of breakthroughs in Agents, Architecture, Training, RAG, and On-Device AI.

attention map tools for huggingface/diffusers

Official implementation for "Stable Flow: Vital Layers for Training-Free Image Editing" [CVPR 2025]

[NeurIPS'23] "MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing".

📚 Collection of awesome generation acceleration resources.

End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).

[CVPR 2024] "MACE: Mass Concept Erasure in Diffusion Models" (Official Implementation)