{"id":13405593,"url":"https://github.com/Stability-AI/stablediffusion","last_synced_at":"2025-03-14T10:31:09.726Z","repository":{"id":63694070,"uuid":"569927055","full_name":"Stability-AI/stablediffusion","owner":"Stability-AI","description":"High-Resolution Image Synthesis with Latent Diffusion Models","archived":false,"fork":false,"pushed_at":"2024-10-10T21:28:57.000Z","size":75202,"stargazers_count":38783,"open_issues_count":288,"forks_count":5000,"subscribers_count":444,"default_branch":"main","last_synced_at":"2024-10-14T16:23:45.659Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Stability-AI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-11-23T23:59:50.000Z","updated_at":"2024-10-14T14:49:46.000Z","dependencies_parsed_at":"2024-09-29T21:50:46.789Z","dependency_job_id":null,"html_url":"https://github.com/Stability-AI/stablediffusion","commit_stats":{"total_commits":32,"total_committers":15,"mean_commits":"2.1333333333333333","dds":0.625,"last_synced_commit":"fc1488421a2761937b9d54784194157882cbc3b1"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Stability-AI%2Fstablediffusion","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Stability-AI%2Fstablediffusion/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Stability-AI%2Fstablediffusion/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Stability-AI%2Fstablediffusion/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Stability-AI","download_url":"https://codeload.github.com/Stability-AI/stablediffusion/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":221458087,"owners_count":16825271,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-07-30T19:02:06.164Z","updated_at":"2025-03-14T10:31:09.719Z","avatar_url":"https://github.com/Stability-AI.png","language":"Python","readme":"# Stable Diffusion Version 2\n![t2i](assets/stable-samples/txt2img/768/merged-0006.png)\n![t2i](assets/stable-samples/txt2img/768/merged-0002.png)\n![t2i](assets/stable-samples/txt2img/768/merged-0005.png)\n\nThis repository contains [Stable Diffusion](https://github.com/CompVis/stable-diffusion) models trained from scratch and will be continuously updated with\nnew checkpoints. The following list provides an overview of all currently available models. More coming soon.\n\n## News\n\n\n**March 24, 2023**\n\n*Stable UnCLIP 2.1*\n\n- New stable diffusion finetune (_Stable unCLIP 2.1_, [Hugging Face](https://huggingface.co/stabilityai/)) at 768x768 resolution,  based on SD2.1-768. This model allows for image variations and mixing operations as described in [*Hierarchical Text-Conditional Image Generation with CLIP Latents*](https://arxiv.org/abs/2204.06125), and, thanks to its modularity, can be combined with other models such as [KARLO](https://github.com/kakaobrain/karlo). Comes in two variants: [*Stable unCLIP-L*](https://huggingface.co/stabilityai/stable-diffusion-2-1-unclip/blob/main/sd21-unclip-l.ckpt) and [*Stable unCLIP-H*](https://huggingface.co/stabilityai/stable-diffusion-2-1-unclip/blob/main/sd21-unclip-h.ckpt), which are conditioned on CLIP ViT-L and ViT-H image embeddings, respectively. Instructions are available [here](doc/UNCLIP.MD).\n\n- A public demo of SD-unCLIP is already available at [clipdrop.co/stable-diffusion-reimagine](https://clipdrop.co/stable-diffusion-reimagine)\n\n\n**December 7, 2022**\n\n*Version 2.1*\n\n- New stable diffusion model (_Stable Diffusion 2.1-v_, [Hugging Face](https://huggingface.co/stabilityai/stable-diffusion-2-1)) at 768x768 resolution and (_Stable Diffusion 2.1-base_, [HuggingFace](https://huggingface.co/stabilityai/stable-diffusion-2-1-base)) at 512x512 resolution, both based on the same number of parameters and architecture as 2.0 and fine-tuned on 2.0, on a less restrictive NSFW filtering of the [LAION-5B](https://laion.ai/blog/laion-5b/) dataset.\nPer default, the attention operation of the model is evaluated at full precision when `xformers` is not installed. To enable fp16 (which can cause numerical instabilities with the vanilla attention module on the v2.1 model) , run your script with `ATTN_PRECISION=fp16 python \u003cthescript.py\u003e`\n\n**November 24, 2022**\n\n*Version 2.0*\n\n- New stable diffusion model (_Stable Diffusion 2.0-v_) at 768x768 resolution. Same number of parameters in the U-Net as 1.5, but uses [OpenCLIP-ViT/H](https://github.com/mlfoundations/open_clip) as the text encoder and is trained from scratch. _SD 2.0-v_ is a so-called [v-prediction](https://arxiv.org/abs/2202.00512) model. \n- The above model is finetuned from _SD 2.0-base_, which was trained as a standard noise-prediction model on 512x512 images and is also made available.\n- Added a [x4 upscaling latent text-guided diffusion model](#image-upscaling-with-stable-diffusion).\n- New [depth-guided stable diffusion model](#depth-conditional-stable-diffusion), finetuned from _SD 2.0-base_. The model is conditioned on monocular depth estimates inferred via [MiDaS](https://github.com/isl-org/MiDaS) and can be used for structure-preserving img2img and shape-conditional synthesis.\n\n  ![d2i](assets/stable-samples/depth2img/depth2img01.png)\n- A [text-guided inpainting model](#image-inpainting-with-stable-diffusion), finetuned from SD _2.0-base_.\n\nWe follow the [original repository](https://github.com/CompVis/stable-diffusion) and provide basic inference scripts to sample from the models.\n\n________________\n*The original Stable Diffusion model was created in a collaboration with [CompVis](https://arxiv.org/abs/2202.00512) and [RunwayML](https://runwayml.com/) and builds upon the work:*\n\n[**High-Resolution Image Synthesis with Latent Diffusion Models**](https://ommer-lab.com/research/latent-diffusion-models/)\u003cbr/\u003e\n[Robin Rombach](https://github.com/rromb)\\*,\n[Andreas Blattmann](https://github.com/ablattmann)\\*,\n[Dominik Lorenz](https://github.com/qp-qp)\\,\n[Patrick Esser](https://github.com/pesser),\n[Björn Ommer](https://hci.iwr.uni-heidelberg.de/Staff/bommer)\u003cbr/\u003e\n_[CVPR '22 Oral](https://openaccess.thecvf.com/content/CVPR2022/html/Rombach_High-Resolution_Image_Synthesis_With_Latent_Diffusion_Models_CVPR_2022_paper.html) |\n[GitHub](https://github.com/CompVis/latent-diffusion) | [arXiv](https://arxiv.org/abs/2112.10752) | [Project page](https://ommer-lab.com/research/latent-diffusion-models/)_\n\nand [many others](#shout-outs).\n\nStable Diffusion is a latent text-to-image diffusion model.\n________________________________\n  \n## Requirements\n\nYou can update an existing [latent diffusion](https://github.com/CompVis/latent-diffusion) environment by running\n\n```\nconda install pytorch==1.12.1 torchvision==0.13.1 -c pytorch\npip install transformers==4.19.2 diffusers invisible-watermark\npip install -e .\n``` \n#### xformers efficient attention\nFor more efficiency and speed on GPUs, \nwe highly recommended installing the [xformers](https://github.com/facebookresearch/xformers)\nlibrary.\n\nTested on A100 with CUDA 11.4.\nInstallation needs a somewhat recent version of nvcc and gcc/g++, obtain those, e.g., via \n```commandline\nexport CUDA_HOME=/usr/local/cuda-11.4\nconda install -c nvidia/label/cuda-11.4.0 cuda-nvcc\nconda install -c conda-forge gcc\nconda install -c conda-forge gxx_linux-64==9.5.0\n```\n\nThen, run the following (compiling takes up to 30 min).\n\n```commandline\ncd ..\ngit clone https://github.com/facebookresearch/xformers.git\ncd xformers\ngit submodule update --init --recursive\npip install -r requirements.txt\npip install -e .\ncd ../stablediffusion\n```\nUpon successful installation, the code will automatically default to [memory efficient attention](https://github.com/facebookresearch/xformers)\nfor the self- and cross-attention layers in the U-Net and autoencoder.\n\n## General Disclaimer\nStable Diffusion models are general text-to-image diffusion models and therefore mirror biases and (mis-)conceptions that are present\nin their training data. Although efforts were made to reduce the inclusion of explicit pornographic material, **we do not recommend using the provided weights for services or products without additional safety mechanisms and considerations.\nThe weights are research artifacts and should be treated as such.**\nDetails on the training procedure and data, as well as the intended use of the model can be found in the corresponding [model card](https://huggingface.co/stabilityai/stable-diffusion-2).\nThe weights are available via [the StabilityAI organization at Hugging Face](https://huggingface.co/StabilityAI) under the [CreativeML Open RAIL++-M License](LICENSE-MODEL). \n\n\n\n## Stable Diffusion v2\n\nStable Diffusion v2 refers to a specific configuration of the model\narchitecture that uses a downsampling-factor 8 autoencoder with an 865M UNet\nand OpenCLIP ViT-H/14 text encoder for the diffusion model. The _SD 2-v_ model produces 768x768 px outputs. \n\nEvaluations with different classifier-free guidance scales (1.5, 2.0, 3.0, 4.0,\n5.0, 6.0, 7.0, 8.0) and 50 DDIM sampling steps show the relative improvements of the checkpoints:\n\n![sd evaluation results](assets/model-variants.jpg)\n\n\n\n### Text-to-Image\n![txt2img-stable2](assets/stable-samples/txt2img/merged-0003.png)\n![txt2img-stable2](assets/stable-samples/txt2img/merged-0001.png)\n\nStable Diffusion 2 is a latent diffusion model conditioned on the penultimate text embeddings of a CLIP ViT-H/14 text encoder.\nWe provide a [reference script for sampling](#reference-sampling-script).\n#### Reference Sampling Script\n\nThis script incorporates an [invisible watermarking](https://github.com/ShieldMnt/invisible-watermark) of the outputs, to help viewers [identify the images as machine-generated](scripts/tests/test_watermark.py).\nWe provide the configs for the _SD2-v_ (768px) and _SD2-base_ (512px) model.\n\nFirst, download the weights for [_SD2.1-v_](https://huggingface.co/stabilityai/stable-diffusion-2-1) and [_SD2.1-base_](https://huggingface.co/stabilityai/stable-diffusion-2-1-base). \n\nTo sample from the _SD2.1-v_ model, run the following:\n\n```\npython scripts/txt2img.py --prompt \"a professional photograph of an astronaut riding a horse\" --ckpt \u003cpath/to/768model.ckpt/\u003e --config configs/stable-diffusion/v2-inference-v.yaml --H 768 --W 768  \n```\nor try out the Web Demo: [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/stabilityai/stable-diffusion).\n\nTo sample from the base model, use\n```\npython scripts/txt2img.py --prompt \"a professional photograph of an astronaut riding a horse\" --ckpt \u003cpath/to/model.ckpt/\u003e --config \u003cpath/to/config.yaml/\u003e  \n```\n\nBy default, this uses the [DDIM sampler](https://arxiv.org/abs/2010.02502), and renders images of size 768x768 (which it was trained on) in 50 steps. \nEmpirically, the v-models can be sampled with higher guidance scales.\n\nNote: The inference config for all model versions is designed to be used with EMA-only checkpoints. \nFor this reason `use_ema=False` is set in the configuration, otherwise the code will try to switch from\nnon-EMA to EMA weights. \n\n#### Enable Intel® Extension for PyTorch* optimizations in Text-to-Image script\n\nIf you're planning on running Text-to-Image on Intel® CPU, try to sample an image with TorchScript and Intel® Extension for PyTorch* optimizations. Intel® Extension for PyTorch* extends PyTorch by enabling up-to-date features optimizations for an extra performance boost on Intel® hardware. It can optimize memory layout of the operators to Channel Last memory format, which is generally beneficial for Intel CPUs, take advantage of the most advanced instruction set available on a machine, optimize operators and many more.\n\n**Prerequisites**\n\nBefore running the script, make sure you have all needed libraries installed. (the optimization was checked on `Ubuntu 20.04`). Install [jemalloc](https://github.com/jemalloc/jemalloc), [numactl](https://linux.die.net/man/8/numactl), Intel® OpenMP and Intel® Extension for PyTorch*.\n\n```bash\napt-get install numactl libjemalloc-dev\npip install intel-openmp\npip install intel_extension_for_pytorch -f https://software.intel.com/ipex-whl-stable\n```\n\nTo sample from the _SD2.1-v_ model with TorchScript+IPEX optimizations, run the following. Remember to specify desired number of instances you want to run the program on ([more](https://github.com/intel/intel-extension-for-pytorch/blob/master/intel_extension_for_pytorch/cpu/launch.py#L48)).\n\n```\nMALLOC_CONF=oversize_threshold:1,background_thread:true,metadata_thp:auto,dirty_decay_ms:9000000000,muzzy_decay_ms:9000000000 python -m intel_extension_for_pytorch.cpu.launch --ninstance \u003cnumber of an instance\u003e --enable_jemalloc scripts/txt2img.py --prompt \\\"a corgi is playing guitar, oil on canvas\\\" --ckpt \u003cpath/to/768model.ckpt/\u003e --config configs/stable-diffusion/intel/v2-inference-v-fp32.yaml  --H 768 --W 768 --precision full --device cpu --torchscript --ipex\n```\n\nTo sample from the base model with IPEX optimizations, use\n\n```\nMALLOC_CONF=oversize_threshold:1,background_thread:true,metadata_thp:auto,dirty_decay_ms:9000000000,muzzy_decay_ms:9000000000 python -m intel_extension_for_pytorch.cpu.launch --ninstance \u003cnumber of an instance\u003e --enable_jemalloc scripts/txt2img.py --prompt \\\"a corgi is playing guitar, oil on canvas\\\" --ckpt \u003cpath/to/model.ckpt/\u003e --config configs/stable-diffusion/intel/v2-inference-fp32.yaml  --n_samples 1 --n_iter 4 --precision full --device cpu --torchscript --ipex\n```\n\nIf you're using a CPU that supports `bfloat16`, consider sample from the model with bfloat16 enabled for a performance boost, like so\n\n```bash\n# SD2.1-v\nMALLOC_CONF=oversize_threshold:1,background_thread:true,metadata_thp:auto,dirty_decay_ms:9000000000,muzzy_decay_ms:9000000000 python -m intel_extension_for_pytorch.cpu.launch --ninstance \u003cnumber of an instance\u003e --enable_jemalloc scripts/txt2img.py --prompt \\\"a corgi is playing guitar, oil on canvas\\\" --ckpt \u003cpath/to/768model.ckpt/\u003e --config configs/stable-diffusion/intel/v2-inference-v-bf16.yaml --H 768 --W 768 --precision full --device cpu --torchscript --ipex --bf16\n# SD2.1-base\nMALLOC_CONF=oversize_threshold:1,background_thread:true,metadata_thp:auto,dirty_decay_ms:9000000000,muzzy_decay_ms:9000000000 python -m intel_extension_for_pytorch.cpu.launch --ninstance \u003cnumber of an instance\u003e --enable_jemalloc scripts/txt2img.py --prompt \\\"a corgi is playing guitar, oil on canvas\\\" --ckpt \u003cpath/to/model.ckpt/\u003e --config configs/stable-diffusion/intel/v2-inference-bf16.yaml --precision full --device cpu --torchscript --ipex --bf16\n```\n\n### Image Modification with Stable Diffusion\n\n![depth2img-stable2](assets/stable-samples/depth2img/merged-0000.png)\n#### Depth-Conditional Stable Diffusion\n\nTo augment the well-established [img2img](https://github.com/CompVis/stable-diffusion#image-modification-with-stable-diffusion) functionality of Stable Diffusion, we provide a _shape-preserving_ stable diffusion model.\n\n\nNote that the original method for image modification introduces significant semantic changes w.r.t. the initial image.\nIf that is not desired, download our [depth-conditional stable diffusion](https://huggingface.co/stabilityai/stable-diffusion-2-depth) model and the `dpt_hybrid` MiDaS [model weights](https://github.com/intel-isl/DPT/releases/download/1_0/dpt_hybrid-midas-501f0c75.pt), place the latter in a folder `midas_models` and sample via \n```\npython scripts/gradio/depth2img.py configs/stable-diffusion/v2-midas-inference.yaml \u003cpath-to-ckpt\u003e\n```\n\nor\n\n```\nstreamlit run scripts/streamlit/depth2img.py configs/stable-diffusion/v2-midas-inference.yaml \u003cpath-to-ckpt\u003e\n```\n\nThis method can be used on the samples of the base model itself.\nFor example, take [this sample](assets/stable-samples/depth2img/old_man.png) generated by an anonymous discord user.\nUsing the [gradio](https://gradio.app) or [streamlit](https://streamlit.io/) script `depth2img.py`, the MiDaS model first infers a monocular depth estimate given this input, \nand the diffusion model is then conditioned on the (relative) depth output.\n\n\u003cp align=\"center\"\u003e\n\u003cb\u003e depth2image \u003c/b\u003e\u003cbr/\u003e\n\u003cimg src=assets/stable-samples/depth2img/d2i.gif\u003e\n\u003c/p\u003e\n\nThis model is particularly useful for a photorealistic style; see the [examples](assets/stable-samples/depth2img).\nFor a maximum strength of 1.0, the model removes all pixel-based information and only relies on the text prompt and the inferred monocular depth estimate.\n\n![depth2img-stable3](assets/stable-samples/depth2img/merged-0005.png)\n\n#### Classic Img2Img\n\nFor running the \"classic\" img2img, use\n```\npython scripts/img2img.py --prompt \"A fantasy landscape, trending on artstation\" --init-img \u003cpath-to-img.jpg\u003e --strength 0.8 --ckpt \u003cpath/to/model.ckpt\u003e\n```\nand adapt the checkpoint and config paths accordingly.\n\n### Image Upscaling with Stable Diffusion\n![upscaling-x4](assets/stable-samples/upscaling/merged-dog.png)\nAfter [downloading the weights](https://huggingface.co/stabilityai/stable-diffusion-x4-upscaler), run\n```\npython scripts/gradio/superresolution.py configs/stable-diffusion/x4-upscaling.yaml \u003cpath-to-checkpoint\u003e\n```\n\nor\n\n```\nstreamlit run scripts/streamlit/superresolution.py -- configs/stable-diffusion/x4-upscaling.yaml \u003cpath-to-checkpoint\u003e\n```\n\nfor a Gradio or Streamlit demo of the text-guided x4 superresolution model.  \nThis model can be used both on real inputs and on synthesized examples. For the latter, we recommend setting a higher \n`noise_level`, e.g. `noise_level=100`.\n\n### Image Inpainting with Stable Diffusion\n\n![inpainting-stable2](assets/stable-inpainting/merged-leopards.png)\n\n[Download the SD 2.0-inpainting checkpoint](https://huggingface.co/stabilityai/stable-diffusion-2-inpainting) and run\n\n```\npython scripts/gradio/inpainting.py configs/stable-diffusion/v2-inpainting-inference.yaml \u003cpath-to-checkpoint\u003e\n```\n\nor\n\n```\nstreamlit run scripts/streamlit/inpainting.py -- configs/stable-diffusion/v2-inpainting-inference.yaml \u003cpath-to-checkpoint\u003e\n```\n\nfor a Gradio or Streamlit demo of the inpainting model. \nThis scripts adds invisible watermarking to the demo in the [RunwayML](https://github.com/runwayml/stable-diffusion/blob/main/scripts/inpaint_st.py) repository, but both should work interchangeably with the checkpoints/configs.  \n\n\n\n## Shout-Outs\n- Thanks to [Hugging Face](https://huggingface.co/) and in particular [Apolinário](https://github.com/apolinario)  for support with our model releases!\n- Stable Diffusion would not be possible without [LAION](https://laion.ai/) and their efforts to create open, large-scale datasets.\n- The [DeepFloyd team](https://twitter.com/deepfloydai) at Stability AI, for creating the subset of [LAION-5B](https://laion.ai/blog/laion-5b/) dataset used to train the model.\n- Stable Diffusion 2.0 uses [OpenCLIP](https://laion.ai/blog/large-openclip/), trained by [Romain Beaumont](https://github.com/rom1504).  \n- Our codebase for the diffusion models builds heavily on [OpenAI's ADM codebase](https://github.com/openai/guided-diffusion)\nand [https://github.com/lucidrains/denoising-diffusion-pytorch](https://github.com/lucidrains/denoising-diffusion-pytorch). \nThanks for open-sourcing!\n- [CompVis](https://github.com/CompVis/stable-diffusion) initial stable diffusion release\n- [Patrick](https://github.com/pesser)'s [implementation](https://github.com/runwayml/stable-diffusion/blob/main/scripts/inpaint_st.py) of the streamlit demo for inpainting.\n- `img2img` is an application of [SDEdit](https://arxiv.org/abs/2108.01073) by [Chenlin Meng](https://cs.stanford.edu/~chenlin/) from the [Stanford AI Lab](https://cs.stanford.edu/~ermon/website/). \n- [Kat's implementation]((https://github.com/CompVis/latent-diffusion/pull/51)) of the [PLMS](https://arxiv.org/abs/2202.09778) sampler, and [more](https://github.com/crowsonkb/k-diffusion).\n- [DPMSolver](https://arxiv.org/abs/2206.00927) [integration](https://github.com/CompVis/stable-diffusion/pull/440) by [Cheng Lu](https://github.com/LuChengTHU).\n- Facebook's [xformers](https://github.com/facebookresearch/xformers) for efficient attention computation.\n- [MiDaS](https://github.com/isl-org/MiDaS) for monocular depth estimation.\n\n\n## License\n\nThe code in this repository is released under the MIT License.\n\nThe weights are available via [the StabilityAI organization at Hugging Face](https://huggingface.co/StabilityAI), and released under the [CreativeML Open RAIL++-M License](LICENSE-MODEL) License.\n\n## BibTeX\n\n```\n@misc{rombach2021highresolution,\n      title={High-Resolution Image Synthesis with Latent Diffusion Models}, \n      author={Robin Rombach and Andreas Blattmann and Dominik Lorenz and Patrick Esser and Björn Ommer},\n      year={2021},\n      eprint={2112.10752},\n      archivePrefix={arXiv},\n      primaryClass={cs.CV}\n}\n```\n\n\n","funding_links":[],"categories":["Python","2 Foundation Models","Table of Contents","Model","👑Stable Diffusion","CV Foundation Model","Artificial Intelligence","Image, Video \u0026 Multimodal Generators","Image \u0026 Vision","MultiModal-ChatLLM","其他_机器视觉","others","Resources","Summary","Repos","2. Business Cases and Implementations","Models","🌐 **Edge Deployment Frameworks**","Libs With Online Books"],"sub_categories":["2.2 Vision Foundation Models","AI - Computer Vision","CV Foundation Model","Python","Android Launcher","网络服务_其他","LLM (Large Language Model)","2.1. CV","Image Generation Models","🍎 **CoreML** - Apple","Philosophy"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FStability-AI%2Fstablediffusion","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FStability-AI%2Fstablediffusion","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FStability-AI%2Fstablediffusion/lists"}