Back to Rankings返回排行榜
Top 100 · Diffusion Models前 100 · 扩散模型
100 repositories sorted by diffusion models 按 扩散模型 排序，共 100 个仓库
| # | Repository仓库 | Stars | Forks | Language语言 | Issues | Description描述 | Last Commit最后提交 |
|---|---|---|---|---|---|---|---|
| 1 | ComfyUI Comfy-Org | 111.5k | 13.0k | Python | 3624 | The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.最强大的模块化扩散模型 GUI、API 和带有图形/节点接口的后端。 | 2026-05-06 |
| 2 | stable-diffusion CompVis | 73.0k | 10.6k | Jupyter Notebook | 538 | A latent text-to-image diffusion model潜在文本到图像的扩散模型 | 2024-06-18 |
| 3 | ControlNet lllyasviel | 33.9k | 3.0k | Python | 438 | Let us control diffusion models!让我们控制扩散模型！ | 2024-02-25 |
| 4 | diffusers huggingface | 33.6k | 7.0k | Python | 716 | 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.🤗 扩散器：PyTorch 中用于生成图像、视频和音频的最先进的扩散模型。 | 2026-05-06 |
| 5 | InvokeAI invoke-ai | 27.1k | 2.8k | TypeScript | 372 | Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, and serves as the foundation for multiple commercial products.Invoke 是稳定扩散模型的领先创意引擎，使专业人士、艺术家和爱好者能够使用最新的人工智能驱动技术生成和创建视觉媒体。该解决方案提供了业界领先的WebUI，并作为多个商业产品的基础。 | 2026-05-05 |
| 6 | IOPaint Sanster | 23.0k | 2.4k | Python | 67 | Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.由 SOTA AI 模型提供支持的图像修复工具。从照片中删除任何不需要的物体、缺陷、人物，或擦除并替换（由稳定扩散驱动）照片上的任何东西。 | 2025-04-29 |
| 7 | latent-diffusion CompVis | 14.0k | 1.7k | Jupyter Notebook | 272 | High-Resolution Image Synthesis with Latent Diffusion Models使用潜在扩散模型的高分辨率图像合成 | 2024-02-29 |
| 8 | Hunyuan3D-2 Tencent-Hunyuan | 13.7k | 1.4k | Python | 217 | High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.使用大规模 Hunyuan3D 扩散模型生成高分辨率 3D 资产。 | 2025-10-28 |
| 9 | DiffSynth-Studio modelscope | 12.4k | 1.2k | Python | 491 | Enjoy the magic of Diffusion models!享受扩散模型的魔力！ | 2026-04-30 |
| 10 | Awesome-Diffusion-Models diff-usion | 12.3k | 1.0k | HTML | 14 | A collection of resources and papers on Diffusion Models有关扩散模型的资源和论文的集合 | 2024-08-01 |
| 11 | HunyuanVideo Tencent-Hunyuan | 12.1k | 1.2k | Python | 158 | HunyuanVideo: A Systematic Framework For Large Video Generation Model混源视频：大视频生成模型的系统框架 | 2025-11-21 |
| 12 | magic-animate magic-research | 10.9k | 1.1k | Python | 96 | [CVPR 2024] Official repository for "MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model"[CVPR 2024]“MagicAnimate：使用扩散模型的时间一致的人类图像动画”的官方存储库 | 2025-08-29 |
| 13 | denoising-diffusion-pytorch lucidrains | 10.5k | 1.3k | Python | 147 | Implementation of Denoising Diffusion Probabilistic Model in Pytorch去噪扩散概率模型在Pytorch中的实现 | 2026-02-11 |
| 14 | ai-toolkit ostris | 10.4k | 1.3k | Python | 54 | The ultimate training toolkit for finetuning diffusion models用于微调扩散模型的终极培训工具包 | 2026-05-05 |
| 15 | runanywhere-sdks RunanywhereAI | 10.4k | 356 | C++ | 32 | Production ready toolkit to run AI locally用于本地运行 AI 的生产就绪工具包 | 2026-05-05 |
| 16 | openvino openvinotoolkit | 10.2k | 3.2k | C++ | 279 | OpenVINO™ is an open source toolkit for optimizing and deploying AI inferenceOpenVINO™ 是一个用于优化和部署 AI 推理的开源工具包 | 2026-05-06 |
| 17 | LTX-Video Lightricks | 10.2k | 997 | Python | 80 | Official repository for LTX-VideoLTX-Video 的官方存储库 | 2026-01-05 |
| 18 | VAR FoundationVision | 8.7k | 566 | Jupyter Notebook | 57 | [NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation![NeurIPS 2024 最佳论文奖][GPT 击败扩散🔥][视觉生成中的缩放法则📈]官方实现。 “视觉自回归建模：通过下一代预测生成可扩展图像”。用于自回归图像生成的*超简单、用户友好且最先进的*代码库！ | 2025-11-10 |
| 19 | DiT facebookresearch | 8.5k | 782 | Python | 67 | Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"“使用 Transformers 的可扩展扩散模型”的官方 PyTorch 实现 | 2024-05-31 |
| 20 | EMO HumanAIGC | 7.6k | 933 | N/A | 246 | Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak ConditionsEmote Portrait Alive：弱条件下使用音视频扩散模型生成富有表现力的人像视频 | 2024-08-21 |
| 21 | lora cloneofsimo | 7.5k | 495 | Jupyter Notebook | 79 | Using Low-rank adaptation to quickly fine-tune diffusion models.使用低秩适应快速微调扩散模型。 | 2024-03-22 |
| 22 | mmagic open-mmlab | 7.4k | 1.1k | Jupyter Notebook | 61 | OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.OpenMMLab 多模式高级、生成和智能创建工具箱。解锁魔法🪄：生成式人工智能 (AIGC)、易于使用的 API、出色的模型动物园、扩散模型，用于文本到图像生成、图像/视频恢复/增强等。 | 2024-08-06 |
| 23 | point-e openai | 6.9k | 799 | Python | 64 | Point cloud diffusion for 3D model synthesis用于 3D 模型合成的点云扩散 | 2024-07-04 |
| 24 | IP-Adapter tencent-ailab | 6.6k | 429 | Jupyter Notebook | 295 | The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt. 图像提示适配器旨在使预训练的文本到图像扩散模型能够生成带有图像提示的图像。 | 2024-06-28 |
| 25 | StyleTTS2 yl4579 | 6.2k | 677 | Python | 103 | StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language ModelsStyleTTS 2：通过大型语音语言模型的风格扩散和对抗性训练实现人类水平的文本转语音 | 2024-08-10 |
| 26 | lora-scripts Akegarasu | 6.0k | 689 | Python | 129 | SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.SD 培训师。 LoRA 和 Dreambooth 训练脚本和 GUI 使用 kohya-ss 的训练器，用于扩散模型。 | 2025-09-08 |
| 27 | stable-diffusion.cpp leejet | 5.9k | 606 | C++ | 358 | Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++纯 C/C++ 中的扩散模型（SD、Flux、Wan、Qwen Image、Z-Image、...）推理 | 2026-04-29 |
| 28 | LatentSync bytedance | 5.7k | 928 | Python | 210 | Taming Stable Diffusion for Lip Sync!驯服稳定的扩散以实现唇形同步！ | 2025-06-20 |
| 29 | Awesome-Video-Diffusion showlab | 5.6k | 357 | N/A | 0 | A curated list of recent diffusion models for video generation, editing, and various other applications.用于视频生成、编辑和各种其他应用的最新扩散模型的精选列表。 | 2026-04-03 |
| 30 | SUPIR Fanghua-Yu | 5.5k | 472 | Python | 109 | SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.SUPIR 旨在开发用于野外逼真图像恢复的实用算法。我们新的在线演示也在suppixel.ai 上发布。 | 2025-05-12 |
| 31 | diffusion hojonathanho | 5.2k | 482 | Python | 21 | Denoising Diffusion Probabilistic Models去噪扩散概率模型 | 2023-08-29 |
| 32 | VideoCrafter AILab-CVC | 5.1k | 410 | Python | 71 | VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion ModelsVideoCrafter2：克服高质量视频扩散模型的数据限制 | 2026-01-09 |
| 33 | IDM-VTON yisol | 5.0k | 812 | Python | 145 | [ECCV2024] IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild[ECCV2024] IDM-VTON：改进真实虚拟野外试穿的扩散模型 | 2025-03-07 |
| 34 | transformerlab-app transformerlab | 4.9k | 510 | Python | 23 | The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardware to GPU clusters.供 AI 研究人员无缝训练、评估和扩展从本地硬件到 GPU 集群的模型的开源研究环境。 | 2026-05-05 |
| 35 | PyTorch-Tutorial-2nd TingsongYu | 4.5k | 483 | Jupyter Notebook | 0 | 《Pytorch实用教程》（第二版）无论是零基础入门，还是CV、NLP、LLM项目应用，或是进阶工程化部署落地，在这里都有。相信在本书的帮助下，读者将能够轻松掌握 PyTorch 的使用，成为一名优秀的深度学习工程师。 | 2025-01-27 |
| 36 | lite.ai.toolkit xlite-dev | 4.4k | 778 | C++ | 0 | 🛠A lite C++ AI toolkit: 100+ models with MNN, ORT and TRT, including Det, Seg, Stable-Diffusion, Face-Fusion, etc.🎉🛠精简版 C++ AI 工具包：100 多个具有 MNN、ORT 和 TRT 的模型，包括 Det、Seg、Stable-Diffusion、Face-Fusion 等。🎉 | 2026-03-19 |
| 37 | Tune-A-Video showlab | 4.4k | 391 | Python | 36 | [ICCV 2023] Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation[ICCV 2023] Tune-A-Video：用于文本到视频生成的图像扩散模型的一次性调整 | 2023-10-25 |
| 38 | diffusion-models-class huggingface | 4.3k | 492 | Jupyter Notebook | 22 | Materials for the Hugging Face Diffusion Models Course拥抱脸部扩散模型课程材料 | 2026-04-17 |
| 39 | Text2Video-Zero Picsart-AI-Research | 4.2k | 386 | Python | 47 | [ICCV 2023 Oral] Text-to-Image Diffusion Models are Zero-Shot Video Generators[ICCV 2023 Oral] 文本到图像扩散模型是零样本视频生成器 | 2023-05-06 |
| 40 | motion-diffusion-model GuyTevet | 4.0k | 452 | Python | 63 | The official PyTorch implementation of the paper "Human Motion Diffusion Model"《人体运动扩散模型》论文的官方 PyTorch 实现 | 2025-10-01 |
| 41 | nunchaku nunchaku-ai | 3.8k | 246 | Python | 4 | [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models[ICLR2025 聚焦] SVDQuant：通过 4 位扩散模型的低阶分量吸收异常值 | 2026-03-07 |
| 42 | improved-diffusion openai | 3.8k | 549 | Python | 104 | Release for Improved Denoising Diffusion Probabilistic Models发布改进的去噪扩散概率模型 | 2024-07-18 |
| 43 | LLaDA ML-GSAI | 3.8k | 264 | Python | 84 | Official PyTorch implementation for "Large Language Diffusion Models"“大型语言扩散模型”的官方 PyTorch 实现 | 2025-11-12 |
| 44 | web-stable-diffusion mlc-ai | 3.7k | 234 | Jupyter Notebook | 34 | Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support. 为网络浏览器带来稳定的扩散模型。一切都在浏览器内运行，没有服务器支持。 | 2024-03-12 |
| 45 | glide-text2im openai | 3.7k | 501 | Python | 23 | GLIDE: a diffusion-based text-conditional image synthesis modelGLIDE：基于扩散的文本条件图像合成模型 | 2024-03-08 |
| 46 | MAGI-1 SandAI-org | 3.7k | 237 | Python | 38 | MAGI-1: Autoregressive Video Generation at ScaleMAGI-1：大规模自回归视频生成 | 2025-06-17 |
| 47 | ComfyUI-LTXVideo Lightricks | 3.6k | 388 | Python | 62 | LTX-Video Support for ComfyUIComfyUI 的 LTX 视频支持 | 2026-04-26 |
| 48 | TurboDiffusion thu-ml | 3.5k | 253 | Python | 68 | TurboDiffusion: 100–200× Acceleration for Video Diffusion ModelsTurboDiffusion：视频扩散模型的 100–200× 加速 | 2026-04-15 |
| 49 | FastVideo hao-ai-lab | 3.4k | 328 | Python | 63 | A unified inference and post-training framework for accelerated video generation.用于加速视频生成的统一推理和后训练框架。 | 2026-05-05 |
| 50 | Diffusion-Models-Papers-Survey-Taxonomy YangLing0818 | 3.3k | 263 | N/A | 5 | Diffusion model papers, survey, and taxonomy扩散模型论文、调查和分类 | 2025-09-27 |
| 51 | Pyramid-Flow jy0205 | 3.2k | 299 | Python | 68 | [ICLR 2025] Pyramidal Flow Matching for Efficient Video Generative Modeling[ICLR 2025] 用于高效视频生成建模的金字塔流匹配 | 2024-12-21 |
| 52 | VGen ali-vilab | 3.2k | 274 | Python | 112 | Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion modelsVGen 的官方存储库：基于扩散模型的视频生成的整体视频生成生态系统 | 2025-01-10 |
| 53 | awesome-speech-recognition-speech-synthesis-papers zzw922cn | 3.1k | 513 | N/A | 1 | Automatic Speech Recognition (ASR), Speaker Verification, Speech Synthesis, Text-to-Speech (TTS), Language Modelling, Singing Voice Synthesis (SVS), Voice Conversion (VC)自动语音识别 (ASR)、说话人验证、语音合成、文本转语音 (TTS)、语言建模、歌声合成 (SVS)、语音转换 (VC) | 2023-10-19 |
| 54 | DreamCraft3D deepseek-ai | 3.0k | 357 | Python | 34 | [ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior[ICLR 2024] DreamCraft3D 的正式实现：采用 Bootstrapped Diffusion Prior 的分层 3D 生成 | 2025-04-22 |
| 55 | SimpleTuner bghira | 2.8k | 279 | Python | 26 | A general fine-tuning kit geared toward image/video/audio diffusion models.适用于图像/视频/音频扩散模型的通用微调套件。 | 2026-05-05 |
| 56 | Kandinsky-2 ai-forever | 2.8k | 319 | Jupyter Notebook | 77 | Kandinsky 2 — multilingual text2image latent diffusion modelKandinsky 2 — 多语言 text2image 潜在扩散模型 | 2024-05-01 |
| 57 | Papers-in-100-Lines-of-Code MaximeVandegar | 2.8k | 248 | Python | 0 | Implementation of papers in 100 lines of code.100行代码实现论文。 | 2026-04-08 |
| 58 | diff-svc prophesier | 2.7k | 817 | Jupyter Notebook | 215 | Singing Voice Conversion via diffusion model通过扩散模型进行歌声转换 | 2026-04-18 |
| 59 | k-diffusion crowsonkb | 2.6k | 400 | Python | 46 | Karras et al. (2022) diffusion models for PyTorch卡拉斯等人。 (2022) PyTorch 的扩散模型 | 2026-02-12 |
| 60 | MimicMotion Tencent | 2.6k | 231 | Python | 89 | High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance具有置信度感知姿势指导的高质量人体运动视频生成 | 2025-11-18 |
| 61 | Stable-Diffusion-Webui-Civitai-Helper butaixianran | 2.5k | 304 | Python | 20 | Stable Diffusion Webui Extension for Civitai, to manage your model much more easily.Civita 的稳定 Diffusion Webui 扩展，可以更轻松地管理您的模型。 | 2026-04-16 |
| 62 | dllm ZHZisZZ | 2.5k | 254 | Python | 12 | dLLM: Simple Diffusion Language ModelingdLLM：简单扩散语言建模 | 2026-04-15 |
| 63 | sd_civitai_extension civitai | 2.4k | 446 | Python | 86 | All of the Civitai models inside Automatic 1111 Stable Diffusion Web UI自动 1111 稳定扩散 Web UI 内的所有 Civitai 模型 | 2024-07-17 |
| 64 | Awesome-Video-Diffusion-Models ChenHsing | 2.3k | 113 | N/A | 0 | [CSUR] A Survey on Video Diffusion Models[CSUR] 视频传播模型调查 | 2026-04-15 |
| 65 | RePaint andreas128 | 2.3k | 199 | Python | 47 | Official PyTorch Code and Models of "RePaint: Inpainting using Denoising Diffusion Probabilistic Models", CVPR 2022“RePaint：使用去噪扩散概率模型进行修复”的官方 PyTorch 代码和模型，CVPR 2022 | 2022-08-20 |
| 66 | Lumina-T2X Alpha-VLLM | 2.3k | 95 | Python | 54 | Lumina-T2X is a unified framework for Text to Any Modality GenerationLumina-T2X 是文本到任何模态生成的统一框架 | 2025-02-16 |
| 67 | LightX2V ModelTC | 2.2k | 195 | Python | 147 | Light Image Video Generation Inference Framework光图像视频生成推理框架 | 2026-05-02 |
| 68 | kimodo nv-tlabs | 2.2k | 233 | Python | 3 | Official implementation of Kimodo, a kinematic motion diffusion model for high-quality human(oid) motion generation.Kimodo 的正式实施，这是一种用于生成高质量人体（oid）运动的运动学运动扩散模型。 | 2026-05-03 |
| 69 | awesome-diffusion-categorized wangkai930418 | 2.2k | 103 | N/A | 1 | collection of diffusion model papers categorized by their subareas按子领域分类的传播模型论文集 | 2026-03-16 |
| 70 | score_sde_pytorch yang-song | 2.1k | 355 | Jupyter Notebook | 56 | PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)通过随机微分方程进行基于分数的生成模型的 PyTorch 实现（ICLR 2021，口头） | 2024-07-14 |
| 71 | audio-diffusion-pytorch archinetai | 2.1k | 179 | Python | 15 | Audio generation using diffusion models, in PyTorch.在 PyTorch 中使用扩散模型生成音频。 | 2023-06-12 |
| 72 | ICEdit River-Zhang | 2.1k | 115 | Python | 23 | [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! [NeurIPS 2025] 图像编辑抵得上一台 LoRA！ 0.1% 的训练数据，实现出色的图像编辑！ ID持久性超越GPT-4o~ MoE ckpt发布！只需 4GB VRAM 就足以运行！ | 2025-12-19 |
| 73 | Awesome-Diffusion-Models-in-Medical-Imaging amirhossein-kz | 2.1k | 171 | N/A | 1 | Diffusion Models in Medical Imaging (Published in Medical Image Analysis Journal)医学成像中的扩散模型（发表于医学图像分析杂志） | 2025-11-17 |
| 74 | zero123plus SUDO-AI-3D | 2.0k | 140 | Python | 28 | Code repository for Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model.Zero123++ 的代码存储库：单图像到一致的多视图扩散基础模型。 | 2024-02-23 |
| 75 | diamond eloialonso | 2.0k | 152 | Python | 5 | DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.DIAMOND（扩散作为环境梦想的模型）是在扩散世界模型中训练的强化学习代理。 NeurIPS 2024 聚焦。 | 2024-12-06 |
| 76 | mmgeneration open-mmlab | 2.0k | 231 | Python | 29 | MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV. MMGeneration 是一个强大的生成模型工具包，基于 PyTorch 和 MMCV。 | 2023-09-05 |
| 77 | anse anse-app | 2.0k | 418 | TypeScript | 39 | Supercharged experience for multiple models such as ChatGPT, DALL-E and Stable Diffusion.ChatGPT、DALL-E 和 Stable Diffusion 等多种模型的增压体验。 | 2025-05-12 |
| 78 | custom-diffusion adobe-research | 2.0k | 142 | Python | 51 | Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)自定义扩散：文本到图像扩散的多概念定制（CVPR 2023） | 2025-12-01 |
| 79 | onediff siliconflow | 2.0k | 129 | Jupyter Notebook | 88 | OneDiff: An out-of-the-box acceleration library for diffusion models.OneDiff：用于扩散模型的开箱即用加速库。 | 2025-12-04 |
| 80 | edm NVlabs | 2.0k | 198 | Python | 16 | Elucidating the Design Space of Diffusion-Based Generative Models (EDM)阐明基于扩散的生成模型 (EDM) 的设计空间 | 2024-03-16 |
| 81 | Awesome-LM-SSP CryptoAILab | 1.9k | 137 | N/A | 0 | A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).大型模型安全、安保和隐私的阅读清单（包括 Awesome LLM Security、Safety 等）。 | 2026-05-02 |
| 82 | LlamaGen FoundationVision | 1.9k | 95 | Python | 71 | Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation自回归模型击败扩散：🦙 Llama 用于可扩展图像生成 | 2024-08-15 |
| 83 | diffusion-pipe tdrussell | 1.9k | 272 | Python | 255 | A pipeline parallel training script for diffusion models.用于扩散模型的管道并行训练脚本。 | 2026-04-25 |
| 84 | Show-o showlab | 1.9k | 91 | Python | 67 | [ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.[ICLR 和 NeurIPS 2025] Show-o 系列存储库，一个 Transformer 来统一多模态理解和生成。 | 2026-01-08 |
| 85 | Make-It-3D junshutang | 1.9k | 137 | Python | 0 | [ICCV 2023] Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior[ICCV 2023] Make-It-3D：利用扩散先验从单个图像创建高保真 3D | 2024-07-05 |
| 86 | dpm-solver LuChengTHU | 1.8k | 135 | Python | 29 | Official code for "DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps" (Neurips 2022 Oral)“DPM-Solver：A Fast ODE Solver for Diffusion Probabilistic Model Sampling in around 10 Steps”的官方代码（Neurips 2022 Oral） | 2024-02-06 |
| 87 | score_sde yang-song | 1.8k | 229 | Jupyter Notebook | 15 | Official code for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)通过随机微分方程进行基于分数的生成模型的官方代码（ICLR 2021，口头） | 2022-11-29 |
| 88 | ddim ermongroup | 1.8k | 234 | Python | 14 | Denoising Diffusion Implicit Models去噪扩散隐式模型 | 2024-07-26 |
| 89 | HunyuanVideo-I2V Tencent-Hunyuan | 1.8k | 191 | Python | 52 | HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideoHunyuanVideo-I2V：基于HunyuanVideo的可定制图像转视频模型 | 2026-04-07 |
| 90 | Palette-Image-to-Image-Diffusion-Models Janspiry | 1.8k | 238 | Python | 34 | Unofficial implementation of Palette: Image-to-Image Diffusion Models by PytorchPalette 的非官方实现：Pytorch 的图像到图像扩散模型 | 2023-07-07 |
| 91 | dreamtalk ali-vilab | 1.8k | 220 | Python | 44 | Official implementations for paper: DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models论文的官方实现：DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models | 2024-01-15 |
| 92 | RAG-Survey hymie122 | 1.8k | 123 | N/A | 3 | Collecting awesome papers of RAG for AIGC. We propose a taxonomy of RAG foundations, enhancements, and applications in paper "Retrieval-Augmented Generation for AI-Generated Content: A Survey".为 AIGC 收集 RAG 的精彩论文。 我们在论文“AI 生成内容的检索增强生成：一项调查”中提出了 RAG 基础、增强功能和应用的分类法。 | 2024-08-20 |
| 93 | Helios PKU-YuanGroup | 1.8k | 134 | Python | 23 | Helios: Real Real-Time Long Video Generation ModelHelios：实时长视频生成模型 | 2026-04-16 |
| 94 | BrushNet TencentARC | 1.7k | 144 | Python | 56 | [ECCV 2024] The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion"【ECCV 2024】论文《BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion》正式实现 | 2024-12-17 |
| 95 | RoboticsDiffusionTransformer thu-ml | 1.7k | 156 | Python | 38 | RDT-1B: a Diffusion Foundation Model for Bimanual ManipulationRDT-1B：用于双手操作的扩散基础模型 | 2026-01-21 |
| 96 | CatVTON Zheng-Chong | 1.7k | 216 | Python | 67 | [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).[ICLR 2025] CatVTON 是一种简单高效的虚拟试戴扩散模型，具有 1) 轻量级网络（总共 899.06M 参数）、2) 参数高效训练（49.57M 可训练参数）和 3) 简化推理（1024X768 分辨率下 < 8G VRAM）。 | 2025-12-16 |
| 97 | ImageReward zai-org | 1.7k | 92 | Python | 58 | [NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation[NeurIPS 2023] ImageReward：学习和评估人类对文本到图像生成的偏好 | 2025-10-29 |
| 98 | MMaDA Gen-Verse | 1.6k | 86 | Python | 44 | MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with block diffusion, mixed-CoT, unified RL)MMaDA - 开源多模态大型扩散语言模型（具有块扩散、混合 CoT、统一 RL 的 dLLM） | 2026-02-14 |
| 99 | fantasy-talking Fantasy-AMAP | 1.6k | 126 | Python | 44 | [ACM MM 2025] FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis[ACM MM 2025] FantasyTalking：通过相干运动合成生成逼真的说话肖像 | 2026-01-26 |
| 100 | Magic123 guochengqian | 1.6k | 99 | Jupyter Notebook | 6 | [ICLR24] Official PyTorch Implementation of Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors[ICLR24] Magic123 的官方 PyTorch 实现：使用 2D 和 3D 扩散先验从一张图像生成高质量 3D 对象 | 2025-05-29 |
No repositories match your search
没有匹配的仓库