generate synthetic scenes for the task of instance/object detection https://github.com/debidatta/syndata-generation
用Unity/PyTorch/fastai生成用于图像分割的合成数据 https://github.com/stratospark/UnityImageSynthesisTutorial1 https://blog.stratospark.com/generating-synthetic-data-image-segmentation-unity-pytorch-fastai.html
https://github.com/MhLiao/SynthText3D 1907.06007
https://github.com/RenYurui/Global-Flow-Local-Attention
https://www.arxiv-vanity.com/papers/2003.02683/
https://github.com/niopeng/SRIM-pytorch
https://github.com/Seanseattle/SMIS
【深度学习Meme生成器】《Meme Generator (MemeGen) Using Deep Learning》 https://medium.com/towards-artificial-intelligence/meme-generator-memegen-using-deep-learning-d133e6fc363f
https://ai.stanford.edu/blog/data-augmentation/
【神经网络纹理自动扩展/生成工具】 https://github.com/photogeniq/texturize
Conditional Image Generation and Manipulation for User-Specified Content https://www.arxiv-vanity.com/papers/2005.04909/
【面向机器人的合成数据：仿真对机器人有用吗？】《Synthetic Data for Robots, Part I: Are Simulations Good For Robotics? | Synthesis AI》 https://synthesis.ai/2020/05/19/synthetic-data-for-robots-part-i-are-simulations-good-for-robotics/
【合成数据：早期做法】 https://synthesis.ai/2020/04/23/synthetic-data-the-early-days-part-i/ https://synthesis.ai/2020/05/05/synthetic-data-the-early-days-part-ii/
【DataGene：用于检测和比较真实数据集和合成数据集之间的数据集相似性】 https://github.com/firmai/datagene
Unsupervised Real-world Low-light Image Enhancement with Decoupled Networks https://www.arxiv-vanity.com/papers/2005.02818/
《Cross-domain Correspondence Learning for Exemplar-based Image Translation》 https://www.arxiv-vanity.com/papers/2004.05571/
Joint Bilateral Learning for Real-time Universal Photorealistic Style Transfer https://arxiv.org/abs/2004.10955
Deep Embedded Clustering with Data Augmentation (DEC-DA). Performance on MNIST (acc=0.985, nmi=0.960). https://github.com/XifengGuo/DEC-DA
【随机分形树】’Random Fractal - Random fractal or the secret behind my tree' https://github.com/victorqribeiro/randomFractal
NAACL 2019: Submodular optimization-based diverse paraphrasing and its effectiveness in data augmentation https://github.com/malllabiisc/DiPS
fast image augmentation library and easy to use wrapper around other libraries https://github.com/albumentations-team/albumentations
Pytorch implementation of the image transformer for unconditional image generation https://github.com/sahajgarg/image_transformer
GarmentGAN: Photo-realistic Adversarial Fashion Transfer https://www.arxiv-vanity.com/papers/2003.01894/
为训练机器学习模型生成多样化合成医学图像数据 https://arxiv.org/abs/1911.08716 https://ai.googleblog.com/2020/02/generating-diverse-synthetic-medical.html
Unsupervised Data Augmentation experiments in PyTorch https://github.com/vfdev-5/UDA-pytorch
Implicit Semantic Data Augmentation for Deep Networks (NeurIPS 2019) https://github.com/blackfeather-wang/ISDA-for-Deep-Networks
Language-based Colorization of Scene Sketches. https://github.com/SketchyScene/SketchySceneColorization
克服自然场景视频理解的大规模标注需求 https://github.com/cmhungsteve/TA3N
【自动生成花卉工笔画】 https://github.com/LingDong-/nonflowers
【用“Contrastive Predictive Coding 2.0”将深度学习需要的标记数据量降低2-5倍】 https://medium.com/@lessw/reducing-your-labeled-data-requirements-2-5x-for-deep-learning-google-brains-new-contrastive-2ac0da0367ef
《Cali-Sketch: Stroke Calibration and Completion for High-Quality Face Image Generation from Poorly-Drawn Sketches》 https://arxiv.org/abs/1911.00426
Data Dive(DeeDive)：自动数据探索(在线)工具，自动完成数据摘要、可视化，用于假设生成、发现数据中的现象/模式 https://www.mooremetrics.com/deedive/
【数据增广综述(资源大列表)】’Data augmentation - List of useful data augmentation resources. You will find here some not common techniques, libraries, links to github repos, papers and others.' https://github.com/AgaMiko/data-augmentation-review
Controlling Style and Semantics in Weakly-Supervised Image Generation https://arxiv.org/abs/1912.03161
PyTorch图像测试时增广 https://github.com/qubvel/ttach
https://github.com/azadis/SB-GAN
https://github.com/NVlabs/few-shot-vid2vid
https://github.com/iVMCL/LostGANs
https://github.com/ashual/scene_generation
Diverse Image Synthesis from Semantic Layouts via Conditional IMLE https://github.com/zth667/Diverse-Image-Synthesis-from-Semantic-Layout
OpenRefine：用于处理、改善杂乱数据的强大开源工具 https://github.com/OpenRefine/OpenRefine
Photo-Realistic Facial Details Synthesis from Single Image https://github.com/apchenstu/Facial_Details_Synthesis
PyTorch implementation of AutoAugment. https://github.com/4uiiurz1/pytorch-auto-augment
Unofficial PyTorch Implementation of Unsupervised Data Augmentation. https://github.com/ildoonet/unsupervised-data-augmentation
This package provides a set of corruptions that can be applied to images in order to benchmark the robustness of neural networks. https://github.com/bethgelab/imagecorruptions
A Pytorch implementation of Fast AutoAugment and EfficientNet https://github.com/JunYeopLee/fast-autoaugment-efficientnet-pytorch
Generative Probabilistic Novelty Detection with Adversarial Autoencoders https://github.com/podgorskiy/GPND
图像增广Albumentations库pytest测试实践 https://medium.com/m/global-identity?redirectUrl=https%3A%2F%2Ftowardsdatascience.com%2Fwriting-test-for-the-image-augmentation-albumentation-library-a73d7bc1caa7
用实际可扩展的能量模型生成训练数据集 https://towardsdatascience.com/generating-training-datasets-using-energy-based-models-that-actually-scale-4e1f83bb9e00
Official implementation of 'FMix: Enhancing Mixed Sampled Data Augmentation' https://github.com/ecs-vlc/FMix
https://github.com/cvlab-epfl/detecting-the-unexpected
【数据增广方法大列表】’Popular Projects - This is a list of awesome methods about data augmentation.' https://github.com/CrazyVertigo/awesome-data-augmentation
用贝叶斯优化发现最适合数据集的图像增广策略 https://github.com/barisozmen/deepaugment
Fast AutoAugment轻量版，自动样本扩增 https://github.com/kakaobrain/autoclint
目标检测数据扩增自动化策略 https://github.com/tensorflow/tpu/tree/master/models/ https://arxiv.org/abs/1906.11172
缺失数据插补算法库 https://github.com/eltonlaw/impyute
学习一下面试用的上，深度学习图像数据扩充的综述，一种数据有限问题的解决方案。A survey on Image Data Augmentation for Deep Learning https://journalofbigdata.springeropen.com/articles/10.1186/s40537-019-0197-0
半监督学习将再度兴起！谷歌祭出大杀器：无监督数据增强 https://mp.weixin.qq.com/s/8vhzTCWeYCDGYzFI6IEF3A
Unsupervised Data Augmentation (UDA) https://arxiv.org/abs/1904.12848 https://github.com/google-research/uda
This is a PyTorch implementation of Generating Diverse High-Fidelity Images with VQ-VAE-2, including their PixelCNN and self-attention priors. https://github.com/unixpickle/vq-vae-2
《Recapture as You Want》 https://www.arxiv-vanity.com/papers/2006.01435/
Rethinking the Truly Unsupervised Image-to-Image Translation https://github.com/clovaai/tunit
Open Compound Domain Adaptation https://github.com/zhmiao/OpenCompoundDomainAdaptation-OCDA
Rethinking Semi-Supervised Learning in VAEs https://github.com/thwjoy/revae-demo
Generating Person Images with Appearance-aware Pose Stylizer https://github.com/siyuhuang/PoseStylizer
The source code for paper "Deep Image Spatial Transformation for Person Image Generation" https://github.com/RenYurui/Global-Flow-Local-Attention
On Feature Normalization and Data Augmentation. https://github.com/Boyiliee/MoEx
Semantically Multi-modal Image Synthesis https://github.com/Seanseattle/SMIS
【用合成数据改进机器学习大规模非平衡数据集】《Improving massively imbalanced datasets in machine learning with synthetic data》
https://github.com/DavHoffmann/Multi-humanDataGeneration
Anime-to-Real Clothing: Cosplay Costume Generation via Image-to-Image Translation https://github.com/tan5o/anime2clothing
https://github.com/aqeelanwar/MaskTheFace
Few-shot Font Generation with Localized Style Representations and Factorization https://github.com/clovaai/lffont
深度学习虚拟试衣——挑战与机遇 https://www.kdnuggets.com/2020/10/deep-learning-virtual-try-clothes.html
虚拟试衣相关资源大列表 https://github.com/minar09/awesome-virtual-try-on
Castle in the Sky: Dynamic Sky Replacement and Harmonization in Videos https://github.com/jiupinjia/SkyAR
https://github.com/ydataai/ydata-synthetic
Few-Shot Font Generation with Deep Metric Learning https://arxiv.org/abs/2011.02206
DTGAN: Dual Attention Generative Adversarial Networks for Text-to-Image Generation https://arxiv.org/abs/2011.02709
https://github.com/facebookresearch/pifuhd
https://github.com/jiupinjia/stylized-neural-painting
《Creative Sketch Generation》 https://github.com/facebookresearch/DoodlerGAN
Unpaired Image-to-Image Translation via Latent Energy Transport https://arxiv.org/abs/2012.00649
RF-GAN: A Light and Reconfigurable Network for Unpaired Image-to-Image Translation https://openaccess.thecvf.com/content/ACCV2020/papers/Koksal_RF-GAN_A_Light_and_Reconfigurable_Network_for_Unpaired_Image-to-Image_Translation_ACCV_2020_paper.pdf
pixelNeRF: Neural Radiance Fields from One or Few Images https://github.com/sxyu/pixel-nerf
Pose-Guided Human Animation from a Single Image in the Wild https://arxiv.org/abs/2012.03796
Full-Glow: Fully conditional Glow for more realistic image generation https://arxiv.org/abs/2012.05846
Unadversarial Examples: Designing Objects for Robust Vision http://gradientscience.org/unadversarial/
Multiavatar，一个开源的头像生成库，可为你生成 120 亿种不同风格的头像 https://github.com/multiavatar/multiavatar-php
合成人视频生成文献列表 https://github.com/yule-li/Human-Video-Generation
ResizeMix: Mixing Data with Preserved Object Information and True Labels https://arxiv.org/abs/2012.11101
像打游戏一样操纵视频生成 paper:《Playable Video Generation》 https://github.com/willi-menapace/PlayableVideoGeneration
https://github.com/Jia-Research-Lab/GridMask
Semantic Image Manipulation Using Scene Graphs https://he-dhamo.github.io/SIMSG/#download
Adversarial score matching and improved sampling for image generation https://github.com/AlexiaJM/AdversarialConsistentScoreMatching
Probing Learning Algorithms with Synthetic Datasets https://github.com/ElementAI/synbols
ForkGAN: Seeing into the rainy night. ECCV 2020 (oral). A task-agnostic image translation framework that can boost multiple vision tasks in adverse weather conditions, including localization, semantic segmentation and object detection. https://github.com/zhengziqiang/ForkGAN
Implementation of Semantic Pyramid for Image Generation https://github.com/rosinality/semantic-pyramid-pytorch
https://github.com/amzn/convolutional-handwriting-gan
This repository contains official code (in MATLAB) for exploring and visualizing HUMBI dataset introduced in the paper "HUMBI: A Large Multiview Dataset of Human Body Expressions" https://github.com/zhixuany/HUMBI
This code repository presents the pytorch implementation of the paper “Structure-Aware Human-ActionGeneration”(ECCV 2020). https://github.com/PingYu-iris/SA-GCN
House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation https://github.com/ennauata/housegan
https://github.com/sysu-imsl/EdgeGAN
The official implement of paper "Unsupervised Few-Shot Learning via Distribution Shift-based Augmentation" https://github.com/WonderSeven/ULDA
The unofficial tensorflow implementation of Swapping Autoencoder for Deep Image Manipulation https://github.com/zhangqianhui/Swapping-Autoencoder-tf
Official PyTorch implementation of 'RELATE: Physically Plausible Multi-Object SceneSynthesis Using Structured Latent Spaces'. https://github.com/hyenal/relate
Learning Temporally Invariant and Localizable Features via Data Augmentation for Video Recognition (ECCVW 2020) https://github.com/taeoh-kim/temporal_data_augmentation
[NeurIPS'20] GradAug: A New Regularization Method for Deep Neural Networks https://github.com/taoyang1122/GradAug
A PyTorch implementation of CVPR2020 paper Adversarial examples improve image recognition https://github.com/tingxueronghua/pytorch-classification-advprop
Exemplar VAE: Linking Generative Models, Nearest Neighbor Retrieval, and Data Augmentation https://github.com/sajadn/Exemplar-VAE
Semantic Image Synthesis via Efficient Class-Adaptive Normalization https://github.com/tzt101/CLADE
Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis https://github.com/gaborvecsei/SLE-GAN
The pytorch implementation for the paper "Self-Supervised Sketch-to-Image Synthesis" in AAAI-2021 https://github.com/odegeasslbc/Self-Supervised-Sketch-to-Image-Synthesis-PyTorch
Code for "OnlineAugment: Online Data Augmentation with Less Domain Knowledge" (ECCV 2020) https://github.com/zhiqiangdon/online-augment
Code for the ECCV2020 paper "Shape and Viewpoint without Keypoints". https://github.com/shubham-goel/ucmr
Flow-based generative model for 3D point clouds. https://github.com/Regenerator/dpf-nets
Official repository for the "Unadversarial Examples: Designing Objects for Robust Vision" paper https://github.com/microsoft/unadversarial
Official implementation of the ICLR 2021 paper "You Only Need Adversarial Supervision for Semantic Image Synthesis" https://github.com/boschresearch/OASIS
Full-Glow: Fully conditional Glow for more realistic image generation https://github.com/MoeinSorkhei/glow2
Colorization Transformer https://github.com/google-research/google-research/tree/master/coltran
Official implementation of the paper Image Generators with Conditionally-Independent Pixel Synthesis https://arxiv.org/abs/2011.13775 https://github.com/saic-mdal/CIPS
K-Hairstyle: A Large-scale Korean hairstyle dataset for virtual hair editing and hairstyle classification https://arxiv.org/abs/2102.06288
SDMetrics：合成数据集质量/功效评价指标 https://github.com/sdv-dev/SDMetrics
Style and Pose Control for Image Synthesis of Humans from a Single Monocular View https://arxiv.org/abs/2102.11263
Domain Generalization: A Survey https://www.arxiv-vanity.com/papers/2103.02503
Official pytorch implementation of paper "Image-to-image Translation via Hierarchical Style Disentanglement" (CVPR 2021 Oral). https://github.com/imlixinyang/HiSD
github.com/omni-us/research-GANwriting
Generating Images with Sparse Representations https://www.arxiv-vanity.com/papers/2103.03841
VectorAscent: 根据文本描述生成矢量图 https://github.com/ajayjain/VectorAscent
《Parser-Free Virtual Try-on via Distilling Appearance Flows》 https://github.com/geyuying/PF-AFN
《HumanGAN: A Generative Model of Humans Images》 https://www.arxiv-vanity.com/papers/2103.06902
《PISE: Person Image Synthesis and Editing with Decoupled GAN》(CVPR 2021) github.com/Zhangjinso/PISE
《Style Augmentation: Data Augmentation via Style Randomization》(CVPRW 2019) github.com/philipjackson/style-augmentation
场景图生成基准 github.com/microsoft/scene_graph_benchmark
https://www.arxiv-vanity.com/papers/2105.06458/
github.com/zheng-yuwei/license-plate-generator
A Distributional Approach to Controlled Text Generation》(ICLR 2021) github.com/naver/gdc
github.com/yinyunie/depth_renderer
《Stochastic Image-to-Video Synthesis using cINNs》(CVPR 2021) github.com/CompVis/image2video-synthesis-using-cINNs
《Diffusion Models Beat GANS on Image Synthesis》(2021) github.com/openai/guided-diffusion
《StylePeople: A Generative Model of Fullbody Human Avatars》(CVPR 2021) github.com/saic-vul/neural-textures
Semi-Supervised Domain Generalization with Stochastic StyleMatch github.com/KaiyangZhou/ssdg-benchmark
Automatic Augmentation Zoo：自动化数据增强库 github.com/Awesome-AutoAug-Algorithms/AWS-OHL-AutoAug
AugLy：面向音频、图像、文本和视频的数据增强库 github.com/facebookresearch/AugLy
NVIDIA Canvas(Beta)：把涂鸦变成画作的应用 www.nvidia.com/en-us/studio/canvas/
Taming Transformers for High-Resolution Image Synthesis github.com/CompVis/taming-transformers
Single Image Texture Translation for Data Augmentation github.com/Boyiliee/SITT
迷你版DALL-E github.com/borisdayma/dalle-mini
Unity Perception: Generate Synthetic Data for Computer Vision github.com/Unity-Technologies/com.unity.perception
《DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort》(CVPR 2021) github.com/nv-tlabs/datasetGAN_release
《Few-shot Semantic Image Synthesis Using StyleGAN Prior》(CoRR 2021) github.com/endo-yuki-t/Fewshot-SMIS
《SeqNet: Learning Descriptors for Sequence-Based Hierarchical Place Recognition》(ICRA 2021) github.com/oravus/seqNet
《AugNet: End-to-End Unsupervised Visual Representation Learning with Image Augmentation》(2021) github.com/chenmingxiang110/AugNet
《Spatially-Adaptive Pixelwise Networks for Fast Image Translation》(CVPR 2021) github.com/tamarott/ASAPNet
《Cross-Modal Contrastive Learning for Text-to-Image Generation》(CVPR 2021) github.com/google-research/xmcgan_image_generation
Explicit Clothing Modeling for an Animatable Full-Body Avatar https://arxiv.org/abs/2106.14879
Generative Art：生成艺术集锦 github.com/erdavids/Generative-Art
3D Human Texture Estimation from a Single Image with Transformers https://arxiv.org/abs/2109.02563
MuarAugment：PyTorch实现的数据扩增搜索算法 github.com/adam-mehdi/MuarAugment
Active label cleaning: Improving dataset quality under resource constraints https://arxiv.org/abs/2109.00574
pixray：神经网络图像生成系统 github.com/dribnet/pixray
https://arxiv.org/abs/2109.07874
DoodleFormer: Creative Sketch Drawing with Transformers https://arxiv.org/abs/2112.03258
pixray：图像生成系统 github.com/pixray/pixray
torchlm：支持100多种数据增强、支持训练和推理的PyTorch标志数据库 github.com/DefTruth/torchlm
Kubric: A scalable dataset generator https://arxiv.org/abs/2203.03570
Interactive Image Synthesis with Panoptic Layout Generation https://arxiv.org/abs/2203.02104
KNN-Diffusion: Image Generation via Large-Scale Retrieval https://arxiv.org/abs/2204.02849
ClothFormer:Taming Video Virtual Try-on in All Module https://arxiv.org/abs/2204.12151
A Comprehensive Survey of Image Augmentation Techniques for Deep Learning https://arxiv.org/abs/2205.01491
SILVR: 合成沉浸式大容量全景数据集 github.com/IDLabMedia/large-lightfields-dataset
Text2Human: Text-Driven Controllable Human Image Generation https://arxiv.org/abs/2205.15996
[CV]《Image Augmentation for Satellite Images》O Adedeji, P Owoade, O Ajayi, O Arowolo [CMU] (2022) https://arxiv.org/abs/2207.14580
【UnstableFusion：(又一款)桌面版Stable Diffusion前端，支持补全、图到图变换等】’UnstableFusion - A Stable Diffusion desktop frontend with inpainting, img2img and more!' by ahrm GitHub: github.com/ahrm/UnstableFusion
【Stable Diffusion入门：创作者指南】《Getting Started With Stable Diffusion: A Guide For Creators》by Jon Stokes https://www.jonstokes.com/p/getting-started-with-stable-diffusion
文字直接生成3D模型的工具 —— DreamFusion 是的，用嘴建模。输入文字，就能生成带深度图和法线的3D模型。 项目地址：dreamfusion3d.github.io
【Video Killed The Radio Star：用生成式AI根据给定音乐自动生成音乐视频】’Video Killed The Radio Star - Notebook and tools for end-to-end automation of music video production with generative AI' by David Marx GitHub: github.com/dmarx/video-killed-the-radio-star
【diffusion-ui：深度学习图像生成前端】’diffusion-ui - Frontend for deeplearning Image generation' by Hanusz Leszek GitHub: github.com/leszekhanusz/diffusion-ui
【make-a-video-pytorch：META最新用文本生成视频模型复现】’make-a-video-pytorch - Implementation of Make-A-Video, new SOTA text to video generator from Meta AI, in Pytorch' by Phil Wang GitHub: github.com/lucidrains/make-a-video-pytorch
【Stable Diffusion in Docker：用Docker运行Stable Diffusion】’Stable Diffusion in Docker - Runs the official Stable Diffusion release in a Docker container.' by fboulnois GitHub: github.com/fboulnois/stable-diffusion-docker
[CV]《Diffusion-based Image Translation using Disentangled Style and Content Representation》G Kwon, J C Ye [KAIST] (2022) https://arxiv.org/abs/2209.15264
[CV]《Imagen Video: High Definition Video Generation with Diffusion Models》J Ho, W Chan, C Saharia, J Whang, R Gao, A Gritsenko, D P. Kingma, B Poole, M Norouzi, D J. Fleet, T Salimans [Google Research] (2022) https://arxiv.org/abs/2210.02303
【文本到图像生成模型提示设计入门指南】《A Beginner’s Guide to Prompt Design for Text-to-Image Generative Models》by Leonie Monigatti towardsdatascience.com/a-beginners-guide-to-prompt-design-for-text-to-image-generative-models-8242e1361580
【stable-diffusion-deploy：大规模提供稳定Stable Diffusion模型服务】’stable-diffusion-deploy - Serve Stable Diffusion model at scale. This app also contains a web UI and a Slack Command Bot that can generate art in your slack workspace' by Lightning AI GitHub: github.com/Lightning-AI/stable-diffusion-deploy
【Shanghai - 本地运行Stable Diffusion生成图像的Discord Bot】’Shanghai - AI Powered Art in a Discord Bot! - A neat Discord bot to run Stable Diffusion locally' by harubaru GitHub: github.com/harubaru/discord-stable-diffusion
【手把手用DreamBooth微调Stable Diffusion (Colab)——用自己的照片生成各种角色的Cos照片】《How to Use DreamBooth to Fine-Tune Stable Diffusion (Colab)》by EdXD https://bytexd.com/how-to-use-dreambooth-to-fine-tune-stable-diffusion-colab/
【AI Render - Stable Diffusion in Blender：Blender的Stable Diffusion插件[酷]】'AI Render - Stable Diffusion in Blender - Stable Diffusion in Blender' by Ben Rugg GitHub: github.com/benrugg/AI-Render
【Stable Diffusion提示创作模板】’Prompt Templates for Stable Diffusion' by Daniel Schosser GitHub: github.com/Dalabad/stable-diffusion-prompt-templates
[CV]《UniTune: Text-Driven Image Editing by Fine Tuning an Image Generation Model on a Single Image》D Valevski, M Kalman, Y Matias, Y Leviathan [Google Research] (2022) https://arxiv.org/abs/2210.09477
【把玩Stable Diffusion的各种方式大列表 】 Github: github.com/sw-yx/prompt-eng/blob/main/README.md#sd-distros
'Yet Another Stable Diffusion Discord Bot' by AmericanPresidentJimmyCarter GitHub: github.com/AmericanPresidentJimmyCarter/yasd-discord-bot
'AWSIM - the best scene simulator for Autoware’ by TIER IV, Inc GitHub: github.com/tier4/AWSIM
【Real-time inference for Stable Diffusion：Stable Diffusion的实时推断(0.88s)】’Real-time inference for Stable Diffusion - 0.88s latency. Covers AITemplate, nvFuser, TensorRT, FlashAttention.' by Stochastic GitHub: github.com/stochasticai/x-stable-diffusion
【Stability.AI Easy Diffusion：扩展版Stable Diffusion Notebook，支持文本到图片、图到图、图像补全、打开和关闭色情过滤、管线缓存等】’Stability.AI Easy Diffusion - Easy Diffusion is an advanced Stable Diffusion Notebook with a feature rich image processing suite.' by Jordan Thompson GitHub: github.com/WASasquatch/easydiffusion
'diffusion for beginners - denoising diffusion models, as simple as possible' by ozanciga GitHub: github.com/ozanciga/diffusion-for-beginners
【Imagic Stable Diffusion基于文本的图片编辑复现】’Imagic training example' by ShivamShrirao GitHub: github.com/ShivamShrirao/diffusers/tree/main/examples/imagic
【stable-diffusion-nvidia-docker：支持GPU的 Dockerfile，用于运行Stability.AI具有简单 Web界面的stable-diffusion模型，包括多GPU支持】'stable-diffusion-nvidia-docker - GPU-ready Dockerfile to run Stability.AI stable-diffusion model with a simple web interface. Includes multi-GPUs support.' by Nicolò Lucchesi GitHub: github.com/NickLucche/stable-diffusion-nvidia-docker
'Aesthetic Gradients - Aesthetic gradients extension for web ui' by AUTOMATIC1111 GitHub: github.com/AUTOMATIC1111/stable-diffusion-webui-aesthetic-gradients
'Stable Diffusion Book |关于 Ai 绘画的全面中文Wiki|入门到入土|开源文档 - 关于使用 Ai 绘画的 Wiki ，翻译，教程，相关资源’ by Jasmine GitHub: github.com/sudoskys/StableDiffusionBook
【迈进Stable Diffusion的世界】《Getting Started in the World of Stable Diffusion | Bipin》 bipinkrishnan.github.io/posts/getting-started-in-the-world-of-stable-diffusion
【DiffusionDB：基于Stable Diffusion的大规模文本到图像提示库数据集】'DiffusionDB - A large-scale text-to-image prompt gallery dataset based on Stable Diffusion' by Polo Club of Data Science GitHub: github.com/poloclub/diffusiondb
【stable-diffusion-pytorch：Stable Diffusion的PyTorch实现】’stable-diffusion-pytorch - Yet another PyTorch implementation of Stable Diffusion' by Jinseo Kim GitHub: github.com/kjsman/stable-diffusion-pytorch
这个Stable Diffusion模型挺有意思 《nitrosocke/archer-diffusion · Hugging Face》 https://huggingface.co/nitrosocke/archer-diffusion
【还有这个Cyberpunk Anime Diffusion】《DGSpitzer/Cyberpunk-Anime-Diffusion · Hugging Face》 https://huggingface.co/DGSpitzer/Cyberpunk-Anime-Diffusion
【Stable Diffusion微调模型集】《Finetuned Diffusion - a Hugging Face Space by anzorq》 https://huggingface.co/spaces/anzorq/finetuned_diffusion
【DALL·E Mini：根据文本提示生成图片的迷你版DALL·E】’DALL·E Mini - DALL·E Mini - Generate images from a text prompt' by Boris Dayma GitHub: github.com/borisdayma/dalle-mini
[CV]《Towards Real-Time Text2Video via CLIP-Guided, Pixel-Level Optimization》P Schaldenbrand, Z Liu, J Oh [CMU] (2022) https://arxiv.org/abs/2210.12826 https://pschaldenbrand.github.io/text2video/
【Naruto diffusion：火影风格的Stable Diffusion微调模型[酷]】《lambdalabs/sd-naruto-diffusers · Hugging Face》 https://huggingface.co/lambdalabs/sd-naruto-diffusers
【Stableboost：快速AI图像与视频生成，简单的交互式提示工程】”Stableboost“ https://stableboost.ai/
【Stable Diffusion提示创作参考手册】《Stable Diffusion Prompt Book - OpenArt | OpenArt》 https://openart.ai/promptbook
【Mubert-Text-to-Music：基于Mubert API根据文字提示自动生成音乐】'Mubert-Text-to-Music - A simple notebook demonstrating prompt-based music generation via Mubert API' by MubertAI GitHub: github.com/MubertAI/Mubert-Text-to-Music
【Basic Dreambooth Guide：Dreambooth基础指南】’Basic Dreambooth Guide' by nitrosocke GitHub: github.com/nitrosocke/dreambooth-training-guide
【DiffusionCraft AI (An InvokeAI Fork)：用Stable Diffusion实时美化Minecraft(我的世界)图像】'DiffusionCraft AI (An InvokeAI Fork) - This version of Stable Diffusion features a slick WebGUI, an interactive command-line script that combines text2img and img2img functionality in a "dream bot" style interface, and multiple features and other enhancements.' by TSF GitHub: github.com/TSFSean/InvokeAI-DiffusionCraftAI
【自然语言提示的时装选型界面，基于对比语言-图像预训练模型】"Inter Alia" https://interalia.vcflab.org/ https://weibo.com/tv/show/1034:4831061180612650?from=old_pc_videoshow
【《创战纪》（TRON: Legacy)风格微调的Stable Diffusion模型】《dallinmackay/Tron-Legacy-diffusion · Hugging Face》 https://huggingface.co/dallinmackay/Tron-Legacy-diffusion
【DiffusionBee：Mac上本地运行的高效Stable Diffusion图形界面App】“DiffusionBee - Stable Diffusion GUI App” https://diffusionbee.com/
GitHub 上的开源技术教程：《Stable Diffusion Book》，关于 AI 绘画的全面中文 Wiki、入门教程、开源文档。 覆盖 AI 绘画相关的术语解释、安装配置、配置与调试、模型训练等相关内容。 GitHub：github.com/sudoskys/StableDiffusionBook
【Stable Diffusion多人协作版】《Stable Diffusion Multiplayer - a Hugging Face Space by huggingface-projects》 https://huggingface.co/spaces/huggingface-projects/stable-diffusion-multiplayer?roomid=room-0
【迪斯尼经典画风微调版Stable Diffusion模型】《nitrosocke/classic-anim-diffusion · Hugging Face》 https://huggingface.co/nitrosocke/classic-anim-diffusion
【用电影《梵高》画面微调的Stable Diffusion模型[酷]】《dallinmackay/Van-Gogh-diffusion · Hugging Face》 https://huggingface.co/dallinmackay/Van-Gogh-diffusion
【在IPhone上运行Stable Diffusion生成图像的App】“Draw Things: AI Generation on the App Store” https://apps.apple.com/pt/app/draw-things-ai-generation/id6444050820?l=en
【diffusers：Huggingface Diffusers的OneFlow移植版，比PyTorch版性能更高】’diffusers - oneflow fork of 🤗 Diffusers' by Oneflow GitHub: github.com/Oneflow-Inc/diffusers
“Taiyi-Stable-Diffusion-1B-Chinese-EN-v0.1 - 首个开源的中英双语Stable Diffusion模型，基于0.2亿筛选过的中文图文对训练” https://huggingface.co/IDEA-CCNL/Taiyi-Stable-Diffusion-1B-Chinese-EN-v0.1
' Stable Diffusion in NCNN with c++' by WuJinxuan GitHub: github.com/EdVince/stable-diffusion-ncnn
'DreamArtist (webui Eextension) - DreamArtist for Stable-Diffusion-webui extension ' by 7eu7d7 GitHub: github.com/7eu7d7/DreamArtist-sd-webui-extension
'Stable Diffusion 2.0 - High-Resolution Image Synthesis with Latent Diffusion Models' by Stability AI GitHub: github.com/Stability-AI/stablediffusion
[CV]《SinDiffusion: Learning a Diffusion Model from a Single Natural Image》W Wang, J Bao, W Zhou, D Chen, D Chen, L Yuan, H Li [University of Science and Technology of China (USTC) & Microsoft Research Asia] (2022) https://arxiv.org/abs/2211.12445
[CV]《SceneComposer: Any-Level Semantic Image Synthesis》Y Zeng, Z Lin, J Zhang, Q Liu, J Collomosse, J Kuen, V M. Patel [Johns Hopkins University & Adobe Research] (2022) https://arxiv.org/abs/2211.11742
【Stable Diffusion 2.0轻量界面】’Lightweight Stable Diffusion v 2.0 web UI' by qunash GitHub: github.com/qunash/stable-diffusion-2-gui
[CV]《Sketch-Guided Text-to-Image Diffusion Models》A Voynov, K Aberman, D Cohen-Or [Google Research] (2022)
https://arxiv.org/abs/2211.13752
【Core ML Stable Diffusion：基于Core ML适用于苹果平台的Stable Diffusion】’Core ML Stable Diffusion - Stable Diffusion with Core ML on Apple Silicon' by Apple GitHub: github.com/apple/ml-stable-diffusion
【像素艺术微调的Stable Diffusion模型】“isopixel-diffusion-v1: Stable Diffusion v2-768 model trained on to generate isometric pixel art · Hugging Face” https://huggingface.co/nerijs/isopixel-diffusion-v1
'diffusers-webui - a Gradio WebUI working with the Diffusers format of Stable Diffusion' by Nitrosocke GitHub: github.com/nitrosocke/diffusers-webui
【Image Generator with Stable Diffusion v2：苹果系统上用Stable Diffusion v2生成图片的开源App】’Image Generator with Stable Diffusion v2 - An iOS app that generates images using Stable Diffusion v2.' by Yasuhito Nagatomo GitHub: github.com/ynagatomo/ImgGenSD2
【OpenAI Image Generator：Node.js+OpenAI实现的根据描述生成图片应用，需要自备API KEY】’OpenAI Image Generator - Web app that uses Node.js and OpenAI to generate images' by Brad Traversy GitHub: github.com/bradtraversy/nodejs-openai-image
'Diffusion Toolkit - an image viewer built in .NET that scans your images for PNGInfo generated by diffusion image generators like AUTOMATIC1111, NovelAI, NKMD and others' by David Khristepher Santos GitHub: github.com/RupertAvery/DiffusionToolkit
AI绘画平台汇总： DALL·E https://openai.com/dall-e-2/ Imagen: Text-to-Image Diffusion Models https://imagen.research.google/ NUWA-Infinity https://nuwa-infinity.microsoft.com/#/ 文心一格 - AI艺术和创意辅助平台 (中文) https://yige.baidu.com/ 6pen Art (中文) https://6pen.art/?invite=173722#no_universal_links Midjourney https://www.midjourney.com/home/ NovelAI https://novelai.net/ AI Art Generator, AI Art Maker - NightCafe Creator https://creator.nightcafe.studio
由浅入深了解Diffusion Model - 知乎 https://zhuanlan.zhihu.com/p/525106459
diffusion model最近在图像生成领域大红大紫，如何看待它的风头开始超过GAN？ - 知乎 https://www.zhihu.com/question/536012286
[CV]《3DHumanGAN: Towards Photo-Realistic 3D-Aware Human Image Generation》Z Yang, S Li, W Wu, B Dai [Shanghai AI Lab & SenseTime Research] (2022) https://arxiv.org/abs/2212.07378
【Riffusion App：基于Stable diffusion的实时音乐生成】’Riffusion App - Stable diffusion for real-time music generation' by Hayk Martiros https://www.riffusion.com/about Web app: github.com/hmartiro/ riffusion-app Inference server: github.com/hmartiro/ riffusion-inference Model checkpoint: huggingface.co/ riffusion/riffusion-model-v1
Karlo：DALL-E 2开源复现版，生成质量挺高， GitHub: github.com/kakaobrain/karlo
【Hugging Face的扩散模型课程】’Hugging Face Diffusion Models Course - Materials for the Hugging Face Diffusion Models Course' by Hugging Face GitHub: github.com/huggingface/diffusion-models-class
【Description：Stable Diffusion 提示创作艺术家列表】’Description - Curated list of artists for Stable Diffusion prompts' Kai Schmidt GitHub: github.com/kaikalii/stable-diffusion-artists
'stable-karlo - Upscaling Karlo text-to-image generation using Stable Diffusion v2.' kpthedev GitHub: github.com/kpthedev/stable-karlo
【手把手指南：花不到$5微调Stable Diffusion模型(Dreambooth)生成花样风格自定义肖像】《Guide for finetuning Stablediffusion with your images | by Vishnu Subramanian | Jan, 2023 | Medium》 http://aicoco.net/s/14
【图解 Stable Diffusion】《The Illustrated Stable Diffusion – Jay Alammar – Visualizing machine learning one concept at a time.》 https://jalammar.github.io/illustrated-stable-diffusion/
'Seth's AI Tools: A Unity based Stable Diffusion front-end for AUTOMATIC1111's WebUI focused on gamedev' Seth Robinson GitHub: github.com/SethRobinson/aitools_client
'SDA: Node - Stable Diffusion Accelerated - 60 steps per second!’ chavinlo GitHub: github.com/chavinlo/sda-node
【Paint by Text：基于生成式 AI 模型通过聊天来修改图片】'Paint by Text - A microsite for InstructPix2Pix, Modify images by chatting with a generative AI model’ Replicate https://paintbytext.chat/?continueFlag=6817c7861421f8b7a171c6db348c259e GitHub: github.com/replicate/paint-by-text
[CV]《Zero-shot Image-to-Image Translation》G Parmar, K K Singh, R Zhang, Y Li, J Lu, J Zhu [CMU & Adobe Research] (2023) https://arxiv.org/abs/2302.03027
【Awesome Diffusion：扩散(Diffusion)相关notebooks、工具、软件、教程等相关资源列表】’Awesome Diffusion - A curated list of awesome Diffusion notebooks, tools, software, tutorials and resources.' Mert Cobanov GitHub: github.com/cobanov/awesome-diffusion
【Breadboard：跨平台 Stable Diffusion 浏览器，用于浏览、搜索和管理机器上用 Stable Diffusion 生成的所有图片】’Breadboard - Stable Diffusion Browser for Windows, Mac, and Linux' cocktailpeanut GitHub: github.com/cocktailpeanut/breadboard
【Web Stable Diffusion：完全在浏览器里运行的 Stable Diffusion，无需服务器即可运行】’Web Stable Diffusion - Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.' mlc-ai GitHub: github.com/mlc-ai/web-stable-diffusion
【用Docker运行并提供REST API接口的的Diffusers / Stable Diffusion】’docker-diffusers-api ("banana-sd-base") - Diffusers / Stable Diffusion in docker with a REST API, supporting various models, pipelines & schedulers.' kiri-art GitHub: github.com/kiri-art/docker-diffusers-api
'SkyPaint-Chinese-EN-v-1.0 - 基于Stable Diffusion优化的AI绘画模型。支持输入中英文文本，可生成多种现代艺术风格的高质量图像' SkyWorkAIGC GitHub: github.com/SkyWorkAIGC/SkyPaint-AI-Diffusion
【sdkit：易于使用的Python库，用于在AI艺术项目中使用Stable Diffusion算法，快速、功能丰富、内存高效】'sdkit - sdkit (stable diffusion kit) is an easy-to-use library for using Stable Diffusion in your AI Art projects. It is fast, feature-packed, and memory-efficient.' easydiffusion GitHub: github.com/easydiffusion/sdkit
https://arxiv.org/abs/2304.03373 [CV]《Training-Free Layout Control with Cross-Attention Guidance》M Chen, I Laina, A Vedaldi [University of Oxford] (2023)
deep-floyd/IF 一个新的开源diffusion模型，看起来生成图片的质量很好。 🔗github.com/deep-floyd/IF
【用自己的数据训练Stable Diffusion模型】’Stable Diffusion Training with MosaicML' by MosaicML GitHub: github.com/mosaicml/diffusion
GeneFace++: 通用和稳定的实时音频驱动的人脸说话视频。 🏡主页：🔗genefaceplusplus.github.io
MultiDiffusion： 融合扩散路径以实现可控的图像生成 应用场景包括：
- 对多张图片进行无缝拼接
- 从文本生成高质量的全景图（比如清河上明图）
- 让图像画在指定区域 等等 项目地址：🔗multidiffusion.github.io/
【Anything To Image： ImageBind+Stable Diffusion相结合，能从任意内容生成图像的工具。利用统一潜空间和Stable Diffusion技术实现图像生成，无需进行训练。可与Diffusers集成，并提供在线演示和Huggingface Gradio的演示。支持的任务包括从音频、音频+文本、音频+图像、图像和文本生成图像】'Anything To Image - Generate image from anything with ImageBind and Stable Diffusion' Zeqiang-Lai GitHub: github.com/Zeqiang-Lai/Anything2Image
StyleDrop是一种通过少量样式图像和文本描述实现任意风格合成的方法，具有极高的灵活性和合成质量。 https://arxiv.org/abs/2306.00983 [CV]《StyleDrop: Text-to-Image Generation in Any Style》K Sohn, N Ruiz, K Lee, D C Chin, I Blok, H Chang, J Barber, L Jiang, G Entis, Y Li, Y Hao, I Essa, M Rubinstein, D Krishnan [Google Research] (2023)
【基于Stable Diffusion图像合成系统的完整C++ ONNX实现，包括原始的txt2img、img2img和修复图像的功能以及安全检查器。该方案不依赖Python，在单进程中运行整个图像生成过程，性能竞争力强，使部署变得更加简单和轻量化，只需要几个可执行文件、库文件和模型权重】’a C++ ONNX implementation of StableDiffusion.' Péter Major GitHub: github.com/axodox/axodox-machinelearning
【Deepshot：全球首个完全可定制的对话生成和替换软件，可生成声音、口形都能以假乱真的口播视频。轻松创作专业级视频，生成完美同步的音频和视频，适用于任何场景。快速生成内容，直观用户界面，用强大的剪辑工具实现创意】 https://deepshot.ai/
根据照片生成3D立体头像 项目地址：sizhean.github.io/panohead 源码：github.com/sizhean/panohead
【Stability AI的生成式模型】’Generative Models by Stability AI' Stability AI GitHub: github.com/Stability-AI/generative-models
【在仅有1GB VRAM的GPU上运行Stable Diffusion】'Tiny optimized Stable-diffusion that can run on GPUs with just 1GB of VRAM.' ThisisBillhe GitHub: github.com/ThisisBillhe/tiny-stable-diffusion
【Segmind-Distill-SD：基于知识蒸馏更小更快的Stable Diffusion版本】'Segmind-Distill-SD - 知识蒸馏，较小的稳定扩散版本' Segmind GitHub: github.com/segmind/distill-sd
【stable-diffusion.cpp：纯C/C++实现的Stable Diffusion，采用类似llama.cpp的方式】’stable-diffusion.cpp - Stable Diffusion in pure C/C++' leejet GitHub: github.com/leejet/stable-diffusion.cpp
用达芬奇手稿微调的Stable Diffusion XL模型 https://replicate.com/cbh123/sdxl-davinci
Würstchen是一个扩散模型，其文本条件组件在高度压缩的图像潜空间工作。压缩数据可以将训练和推理的计算成本降低几个数量级。Würstchen通过新设计实现了42倍的空间压缩 https://huggingface.co/blog/wuertschen
stable diffusion原理解读通俗易懂，史诗级万字爆肝长文 https://mp.weixin.qq.com/s/WbbotOH-awemHxSkw5X_Iw
【AI生成图像作为数据源相关文献列表】’AI-Generated Images as Data Source: The Dawn of Synthetic Era [Paper]' Zuhao Yang GitHub: github.com/mwxely/AIGS
【MIMIC-CXR-VQA：医学领域的视觉问答(VQA)任务的复杂、多样和大规模数据集】’MIMIC-CXR-VQA - A new collection of medical visual question answering dataset on MIMIC-CXR database' baeseongsu GitHub: github.com/baeseongsu/mimic-cxr-vqa
【Stable Fast：用于 HuggingFace Diffusers 在 NVIDIA GPU 上进行推断优化的超轻量推断优化库】'Stable Fast - An ultra lightweight inference performance optimization library for HuggingFace Diffusers on NVIDIA GPUs.' chengzeyi GitHub: github.com/chengzeyi/stable-fast
【Seg2Sat：利用Stable Diffusion算法和ControlNet合成航拍图像，数据集源自IGN的FLAIR（法国航空图像地面覆盖数据），用于法国各地区的地面覆盖信息】’Seg2Sat - Segmentation to aerial view using pretrained diffuser models - Using StableDiffusion and ControlNet to generate synthetic aerial images' Retronyme GitHub: github.com/RubenGres/Seg2Sat
【SSD-1B：用于文本到图像生成的模型，相比其前身Stable Diffusion XL(SDXL)，提供了60%的速度提升。该模型经过多样的数据集训练，包括Grit和Midjourney的数据，因此能够根据文本提示生成各种视觉内容】《Segmind Stable Diffusion 1B (SSD-1B) Model Card | segmind/SSD-1B · Hugging Face》 https://huggingface.co/segmind/SSD-1B github.com/segmind/SSD-1B
【Kandinsky-3: 基于 Kandinsky2-x 模型族构建的开源文本到图像扩散模型】'Kandinsky-3: Text-to-image diffusion model' by AI Forever GitHub: github.com/ai-forever/Kandinsky-3
【Stable Diffusion web UI with DirectML：基于Gradio库的Stable Diffusion的浏览器界面，提供了各种功能，包括文本到图像、图像到图像模式、生成高分辨率图像等】'Stable Diffusion web UI with DirectML - A browser interface based on Gradio library for Stable Diffusion' Seunghoon Lee GitHub: github.com/lshqqytiger/stable-diffusion-webui-directml
https://huggingface.co/spaces/yuvalalaluf/cross-image-attention
SDXL Turbo，Stability AI 推出的实时文本到图像生成模型。速度超快。 详细介绍：stability.ai/news/stability-ai-sdxl-turbo
上海人工智能实验室的视频生成模型开源项目 Vchitect 📽️LaVie (Text2Video Model)
- Code: github.com/Vchitect/LaVie
- huggingface.co/spaces/Vchitect/LaVie 网页链接 📽️SEINE (Image2Video Model)
- Code: github.com/Vchitect/SEINE
- huggingface.co/spaces/Vchitect/SEINE
北邮 清华 英国萨里大学 英国爱丁堡大学的一项研究，DemoFusion，让AI绘制高分辨率图像的成本更低。在单张RTX 3090 GPU上就能生成高分辨率图片（如4k图片） 地址：ruoyidu.github.io/demofusion/demofusion.html