stablediffusion - 潜在拡散モデルを用いた高解像度画像合成

(High-Resolution Image Synthesis with Latent Diffusion Models)

Created at: 2022-11-24 07:59:50

Language: Python

URL: https://github.com/Stability-AI/stablediffusion

License: MIT

安定拡散バージョン2

このリポジトリには、ゼロからトレーニングされた安定した拡散モデルが含まれており、継続的に更新されます。新しいチェックポイント。次の一覧は、現在使用可能なすべてのモデルの概要を示しています。詳細は近日公開予定です。

ニュース

2022年12月7日

バージョン 2.1

新しい安定拡散モデル(安定拡散2.1-v、ハギングフェイス)768x768解像度と512x512解像度(安定拡散2.1ベース、ハギングフェイス)は、どちらも2.0と同じ数のパラメータとアーキテクチャに基づいており、2.0で微調整されています。データセット。デフォルトでは、モデルのアテンション操作は、がインストールされていないときに最大精度で評価されます。fp16を有効にするには(v2.1モデルのバニラアテンションモジュールで数値が不安定になる可能性があります)、スクリプトを次のように実行します。
```
xformers
```
```
ATTN_PRECISION=fp16 python <thescript.py>
```

2022年11月24日

バージョン 2.0

768x768の解像度での新しい安定拡散モデル(安定拡散2.0-v)。U-Netのパラメータ数は1.5と同じですが、テキストエンコーダとしてOpenCLIP-ViT/Hを使用し、最初からトレーニングされます。SD 2.0-vは、いわゆるv予測モデルです。
上記のモデルは、512x512の画像で標準のノイズ予測モデルとして学習されたSD 2.0ベースから微調整されており、利用可能でもあります。
x4 アップスケーリングの潜在テキスト誘導拡散モデルを追加しました。
SD 2.0ベースから微調整された新しい深度ガイド付き安定拡散モデル。このモデルは、MiDaSを介して推定された単眼深さ推定値に基づいて調整されており、構造保存img2imgおよび形状条件付き合成に使用できます。
SD 2.0ベースから微調整されたテキストガイド付きインペインティングモデル。

元のリポジトリに従い、モデルからサンプリングするための基本的な推論スクリプトを提供します。

オリジナルの安定拡散モデルは、CompVisおよびRunwayMLとのコラボレーションで作成され、次の作業に基づいて構築されています。

潜在拡散モデル
を用いた高解像度画像合成ロビン・ロンバッハ*、アンドレアス・ブラットマン*、ドミニク・ローレンツ、パトリック・エッサー、ビョルン・オマー
CVPR '22 口頭|GitHub |arXiv |プロジェクトページ

そして他の多く。

安定拡散は、潜在的なテキストから画像への拡散モデルです。

必要条件

既存の潜在拡散環境を更新するには、

conda install pytorch==1.12.1 torchvision==0.13.1 -c pytorch
pip install transformers==4.19.2 diffusers invisible-watermark
pip install -e .

Xformersの効率的な注意

GPUの効率と速度を向上させるには、 Xformersライブラリをインストールすることを強くお勧めします。

CUDA 11.4を搭載したA100でテスト済み。インストールには、nvccとgcc / g ++のやや新しいバージョンが必要です。

export CUDA_HOME=/usr/local/cuda-11.4
conda install -c nvidia/label/cuda-11.4.0 cuda-nvcc
conda install -c conda-forge gcc
conda install -c conda-forge gxx_linux-64=9.5.0

Then, run the following (compiling takes up to 30 min).

cd ..
git clone https://github.com/facebookresearch/xformers.git
cd xformers
git submodule update --init --recursive
pip install -r requirements.txt
pip install -e .
cd ../stablediffusion

Upon successful installation, the code will automatically default to memory efficient attention for the self- and cross-attention layers in the U-Net and autoencoder.

General Disclaimer

Stable Diffusion models are general text-to-image diffusion models and therefore mirror biases and (mis-)conceptions that are present in 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. The weights are research artifacts and should be treated as such. Details on the training procedure and data, as well as the intended use of the model can be found in the corresponding model card. The weights are available via the StabilityAI organization at Hugging Face under the CreativeML Open RAIL++-M License.

Stable Diffusion v2

Stable Diffusion v2 refers to a specific configuration of the model architecture that uses a downsampling-factor 8 autoencoder with an 865M UNet and OpenCLIP ViT-H/14 text encoder for the diffusion model. The SD 2-v model produces 768x768 px outputs.

Evaluations with different classifier-free guidance scales (1.5, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0) and 50 DDIM sampling steps show the relative improvements of the checkpoints:

Text-to-Image

Stable Diffusion 2 is a latent diffusion model conditioned on the penultimate text embeddings of a CLIP ViT-H/14 text encoder. We provide a reference script for sampling.

Reference Sampling Script

This script incorporates an invisible watermarking of the outputs, to help viewers identify the images as machine-generated. We provide the configs for the SD2-v (768px) and SD2-base (512px) model.

First, download the weights for SD2.1-v and SD2.1-base.

To sample from the SD2.1-v model, run the following:

python scripts/txt2img.py --prompt "a professional photograph of an astronaut riding a horse" --ckpt <path/to/768model.ckpt/> --config configs/stable-diffusion/v2-inference-v.yaml --H 768 --W 768

or try out the Web Demo: .

To sample from the base model, use

python scripts/txt2img.py --prompt "a professional photograph of an astronaut riding a horse" --ckpt <path/to/model.ckpt/> --config <path/to/config.yaml/>

By default, this uses the DDIM sampler, and renders images of size 768x768 (which it was trained on) in 50 steps. Empirically, the v-models can be sampled with higher guidance scales.

Note: The inference config for all model versions is designed to be used with EMA-only checkpoints. For this reason

use_ema=False

is set in the configuration, otherwise the code will try to switch from non-EMA to EMA weights.

Image Modification with Stable Diffusion

Depth-Conditional Stable Diffusion

To augment the well-established img2img functionality of Stable Diffusion, we provide a shape-preserving stable diffusion model.

Note that the original method for image modification introduces significant semantic changes w.r.t. the initial image. If that is not desired, download our depth-conditional stable diffusion model and the

dpt_hybrid

MiDaS model weights, place the latter in a folder

midas_models

and sample via

python scripts/gradio/depth2img.py configs/stable-diffusion/v2-midas-inference.yaml <path-to-ckpt>

streamlit run scripts/streamlit/depth2img.py configs/stable-diffusion/v2-midas-inference.yaml <path-to-ckpt>

This method can be used on the samples of the base model itself. For example, take this sample generated by an anonymous discord user. Using the gradio or streamlit script

depth2img.py

, the MiDaS model first infers a monocular depth estimate given this input, and the diffusion model is then conditioned on the (relative) depth output.

depth2image

This model is particularly useful for a photorealistic style; see the examples. For 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.

Classic Img2Img

For running the "classic" img2img, use

python scripts/img2img.py --prompt "A fantasy landscape, trending on artstation" --init-img <path-to-img.jpg> --strength 0.8 --ckpt <path/to/model.ckpt>

and adapt the checkpoint and config paths accordingly.

Image Upscaling with Stable Diffusion

After downloading the weights, run

python scripts/gradio/superresolution.py configs/stable-diffusion/x4-upscaling.yaml <path-to-checkpoint>

streamlit run scripts/streamlit/superresolution.py -- configs/stable-diffusion/x4-upscaling.yaml <path-to-checkpoint>

for a Gradio or Streamlit demo of the text-guided x4 superresolution model.
This model can be used both on real inputs and on synthesized examples. For the latter, we recommend setting a higher

noise_level

, e.g.

noise_level=100

Image Inpainting with Stable Diffusion

Download the SD 2.0-inpainting checkpoint and run

python scripts/gradio/inpainting.py configs/stable-diffusion/v2-inpainting-inference.yaml <path-to-checkpoint>

streamlit run scripts/streamlit/inpainting.py -- configs/stable-diffusion/v2-inpainting-inference.yaml <path-to-checkpoint>

for a Gradio or Streamlit demo of the inpainting model. This scripts adds invisible watermarking to the demo in the RunwayML repository, but both should work interchangeably with the checkpoints/configs.

Shout-Outs

Thanks to Hugging Face and in particular Apolinário for support with our model releases!
Stable Diffusion would not be possible without LAION and their efforts to create open, large-scale datasets.
The DeepFloyd team at Stability AI, for creating the subset of LAION-5B dataset used to train the model.
Stable Diffusion 2.0 uses OpenCLIP, trained by Romain Beaumont.
Our codebase for the diffusion models builds heavily on OpenAI's ADM codebase and https://github.com/lucidrains/denoising-diffusion-pytorch. Thanks for open-sourcing!
CompVis initial stable diffusion release
Patrick's implementation of the streamlit demo for inpainting.
```
img2img
```
is an application of SDEdit by Chenlin Meng from the Stanford AI Lab.
Kat's implementation of the PLMS sampler, and more.
DPMSolver integration by Cheng Lu.
Facebook's xformers for efficient attention computation.
MiDaS for monocular depth estimation.

License

The code in this repository is released under the MIT License.

The weights are available via the StabilityAI organization at Hugging Face, and released under the CreativeML Open RAIL++-M License License.

BibTeX

@misc{rombach2021highresolution,
      title={High-Resolution Image Synthesis with Latent Diffusion Models}, 
      author={Robin Rombach and Andreas Blattmann and Dominik Lorenz and Patrick Esser and Björn Ommer},
      year={2021},
      eprint={2112.10752},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}