Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/darkhemic/stable-diffusion-cpuonly

a fork that installs runs on pytorch cpu-only
https://github.com/darkhemic/stable-diffusion-cpuonly

Last synced: about 1 month ago
JSON representation

a fork that installs runs on pytorch cpu-only

Awesome Lists containing this project

README 

        
# Stable Diffusion CPU only



This fork of Stable-Diffusion doesn't require a high end graphics card and runs exclusively on your cpu. It's been tested on Linux Mint 22.04 and Windows 10.



This isn't the fastest experience you'll have with stable diffusion but it does allow you to use it and most of the current set of features floating around on the internet such as txt2img, img2img, image upscaling with Real-ESRGAN and better faces with GFPGAN.



A install guide video is located here. https://www.youtube.com/watch?v=mTrA4uDiKzU&t=644s



##

  

## Requirements



### Windows and Linux requirements



Install Anaconda

https://www.anaconda.com/

Yes even on a linux system anaconda needs to be installed. 



### Windows 



##### Install Visual Studio Community Edition to build 1 file. 

Click on the free download and make sure to check "Desktop Development with C++" when installing as per this image

(https://learn.microsoft.com/en-us/cpp/get-started/media/vs2022-installer-workloads.png?view=msvc-170)



https://visualstudio.microsoft.com/downloads/?q=build+tools



##### Install Git

https://git-scm.com/downloads

version control manager for code 

we just use it to download repos from GitHub

Must be on system PATH, When installing select the option add to system PATH



##### Install Wget

used to download models for projects

Windows users need this verison

https://eternallybored.org/misc/wget/

download the .exe and I copied it to my C:/Windows/System directory (this isn't the correct way just the fastest to get it working)



reboot your system just to make sure everything is properly loaded up.



### Linux Mint 22.04



Install git and wget with the following command

```

sudo apt-get -y install git wget build-essential

```

## Installation of Stable-Diffusion-cpuonly



### Download Stable-Diffusion-cpuonly



Copy this github repository and extract the files.



### Download the CompVis Stable-diffusion model.



Go here and download the correct mode from here. You'll have to agree to the license setup an account but this is the bread and butter AI art generating learning model.



https://huggingface.co/CompVis/stable-diffusion-v-1-4-original



copy the file to your stable-diffusion-cpuonly-main directory



### Download the GFPGAN model



https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth



copy the file to your stable-diffusion-cpuponly-main directory



### Windows - Running the install script



open a terminal or powershell and cd to your stable-diffusion-cpuonly-main directory and run

```

.\install_sdco.bat

```



### Linux - Running the install script

open a terminal or powershell and cd to your stable-diffusion-cpuonly-main directory and run

```

bash -i install_sdco.sh

```



## Windows - Starting Stable-Diffusion-cpuonly



Run the following command



```

.\run_sdco.bat

```

## Linux - Starting Stable-Diffusion-cpuonly



Run the following command



```

bash -i run_sdco.sh

```



# Stable Diffusion

*Stable Diffusion was made possible thanks to a collaboration with [Stability AI](https://stability.ai/) and [Runway](https://runwayml.com/) and builds upon our previous work:*



[**High-Resolution Image Synthesis with Latent Diffusion Models**](https://ommer-lab.com/research/latent-diffusion-models/)


[Robin Rombach](https://github.com/rromb)\*,

[Andreas Blattmann](https://github.com/ablattmann)\*,

[Dominik Lorenz](https://github.com/qp-qp)\,

[Patrick Esser](https://github.com/pesser),

[Björn Ommer](https://hci.iwr.uni-heidelberg.de/Staff/bommer)


_[CVPR '22 Oral](https://openaccess.thecvf.com/content/CVPR2022/html/Rombach_High-Resolution_Image_Synthesis_With_Latent_Diffusion_Models_CVPR_2022_paper.html) |

[GitHub](https://github.com/CompVis/latent-diffusion) | [arXiv](https://arxiv.org/abs/2112.10752) | [Project page](https://ommer-lab.com/research/latent-diffusion-models/)_



![txt2img-stable2](assets/stable-samples/txt2img/merged-0006.png)

[Stable Diffusion](#stable-diffusion-v1) is a latent text-to-image diffusion

model.

Thanks to a generous compute donation from [Stability AI](https://stability.ai/) and support from [LAION](https://laion.ai/), we were able to train a Latent Diffusion Model on 512x512 images from a subset of the [LAION-5B](https://laion.ai/blog/laion-5b/) database. 

Similar to Google's [Imagen](https://arxiv.org/abs/2205.11487), 

this model uses a frozen CLIP ViT-L/14 text encoder to condition the model on text prompts.

With its 860M UNet and 123M text encoder, the model is relatively lightweight and runs on a GPU with at least 10GB VRAM.

See [this section](#stable-diffusion-v1) below and the [model card](https://huggingface.co/CompVis/stable-diffusion).



##



## Stable Diffusion v1



Stable Diffusion v1 refers to a specific configuration of the model

architecture that uses a downsampling-factor 8 autoencoder with an 860M UNet

and CLIP ViT-L/14 text encoder for the diffusion model. The model was pretrained on 256x256 images and 

then finetuned on 512x512 images.



*Note: Stable Diffusion v1 is a general text-to-image diffusion model and therefore mirrors biases and (mis-)conceptions that are present

in its training data. 

Details on the training procedure and data, as well as the intended use of the model can be found in the corresponding [model card](Stable_Diffusion_v1_Model_Card.md).*



The weights are available via [the CompVis organization at Hugging Face](https://huggingface.co/CompVis) under [a license which contains specific use-based restrictions to prevent misuse and harm as informed by the model card, but otherwise remains permissive](LICENSE). While commercial use is permitted under the terms of the license, **we do not recommend using the provided weights for services or products without additional safety mechanisms and considerations**, since there are [known limitations and biases](Stable_Diffusion_v1_Model_Card.md#limitations-and-bias) of the weights, and research on safe and ethical deployment of general text-to-image models is an ongoing effort. **The weights are research artifacts and should be treated as such.**



[The CreativeML OpenRAIL M license](LICENSE) is an [Open RAIL M license](https://www.licenses.ai/blog/2022/8/18/naming-convention-of-responsible-ai-licenses), adapted from the work that [BigScience](https://bigscience.huggingface.co/) and [the RAIL Initiative](https://www.licenses.ai/) are jointly carrying in the area of responsible AI licensing. See also [the article about the BLOOM Open RAIL license](https://bigscience.huggingface.co/blog/the-bigscience-rail-license) on which our license is based.



### Weights



We currently provide the following checkpoints:



- `sd-v1-1.ckpt`: 237k steps at resolution `256x256` on [laion2B-en](https://huggingface.co/datasets/laion/laion2B-en).

  194k steps at resolution `512x512` on [laion-high-resolution](https://huggingface.co/datasets/laion/laion-high-resolution) (170M examples from LAION-5B with resolution `>= 1024x1024`).

- `sd-v1-2.ckpt`: Resumed from `sd-v1-1.ckpt`.

  515k steps at resolution `512x512` on [laion-aesthetics v2 5+](https://laion.ai/blog/laion-aesthetics/) (a subset of laion2B-en with estimated aesthetics score `> 5.0`, and additionally

filtered to images with an original size `>= 512x512`, and an estimated watermark probability `< 0.5`. The watermark estimate is from the [LAION-5B](https://laion.ai/blog/laion-5b/) metadata, the aesthetics score is estimated using the [LAION-Aesthetics Predictor V2](https://github.com/christophschuhmann/improved-aesthetic-predictor)).

- `sd-v1-3.ckpt`: Resumed from `sd-v1-2.ckpt`. 195k steps at resolution `512x512` on "laion-aesthetics v2 5+" and 10\% dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).

- `sd-v1-4.ckpt`: Resumed from `sd-v1-2.ckpt`. 225k steps at resolution `512x512` on "laion-aesthetics v2 5+" and 10\% dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).



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 PLMS sampling

steps show the relative improvements of the checkpoints:

![sd evaluation results](assets/v1-variants-scores.jpg)



### Text-to-Image with Stable Diffusion

![txt2img-stable2](assets/stable-samples/txt2img/merged-0005.png)

![txt2img-stable2](assets/stable-samples/txt2img/merged-0007.png)



Stable Diffusion is a latent diffusion model conditioned on the (non-pooled) text embeddings of a CLIP ViT-L/14 text encoder.

We provide a [reference script for sampling](#reference-sampling-script), but

there also exists a [diffusers integration](#diffusers-integration), which we

expect to see more active community development.



#### Reference Sampling Script



We provide a reference sampling script, which incorporates



- a [Safety Checker Module](https://github.com/CompVis/stable-diffusion/pull/36),

  to reduce the probability of explicit outputs,

- 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).



After [obtaining the `stable-diffusion-v1-*-original` weights](#weights), link them

```

mkdir -p models/ldm/stable-diffusion-v1/

ln -s  models/ldm/stable-diffusion-v1/model.ckpt 

```

and sample with

```

python scripts/txt2img.py --prompt "a photograph of an astronaut riding a horse" --plms 

```



By default, this uses a guidance scale of `--scale 7.5`, [Katherine Crowson's implementation](https://github.com/CompVis/latent-diffusion/pull/51) of the [PLMS](https://arxiv.org/abs/2202.09778) sampler, 

and renders images of size 512x512 (which it was trained on) in 50 steps. All supported arguments are listed below (type `python scripts/txt2img.py --help`).



```commandline

usage: txt2img.py [-h] [--prompt [PROMPT]] [--outdir [OUTDIR]] [--skip_grid] [--skip_save] [--ddim_steps DDIM_STEPS] [--plms] [--laion400m] [--fixed_code] [--ddim_eta DDIM_ETA]

                  [--n_iter N_ITER] [--H H] [--W W] [--C C] [--f F] [--n_samples N_SAMPLES] [--n_rows N_ROWS] [--scale SCALE] [--from-file FROM_FILE] [--config CONFIG] [--ckpt CKPT]

                  [--seed SEED] [--precision {full,autocast}]



optional arguments:

  -h, --help            show this help message and exit

  --prompt [PROMPT]     the prompt to render

  --outdir [OUTDIR]     dir to write results to

  --skip_grid           do not save a grid, only individual samples. Helpful when evaluating lots of samples

  --skip_save           do not save individual samples. For speed measurements.

  --ddim_steps DDIM_STEPS

                        number of ddim sampling steps

  --plms                use plms sampling

  --laion400m           uses the LAION400M model

  --fixed_code          if enabled, uses the same starting code across samples

  --ddim_eta DDIM_ETA   ddim eta (eta=0.0 corresponds to deterministic sampling

  --n_iter N_ITER       sample this often

  --H H                 image height, in pixel space

  --W W                 image width, in pixel space

  --C C                 latent channels

  --f F                 downsampling factor

  --n_samples N_SAMPLES

                        how many samples to produce for each given prompt. A.k.a. batch size

  --n_rows N_ROWS       rows in the grid (default: n_samples)

  --scale SCALE         unconditional guidance scale: eps = eps(x, empty) + scale * (eps(x, cond) - eps(x, empty))

  --from-file FROM_FILE

                        if specified, load prompts from this file

  --config CONFIG       path to config which constructs model

  --ckpt CKPT           path to checkpoint of model

  --seed SEED           the seed (for reproducible sampling)

  --precision {full,autocast}

                        evaluate at this precision

```

Note: The inference config for all v1 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. If you want to examine the effect of EMA vs no EMA, we provide "full" checkpoints

which contain both types of weights. For these, `use_ema=False` will load and use the non-EMA weights.



#### Diffusers Integration



A simple way to download and sample Stable Diffusion is by using the [diffusers library](https://github.com/huggingface/diffusers/tree/main#new--stable-diffusion-is-now-fully-compatible-with-diffusers):

```py

# make sure you're logged in with `huggingface-cli login`

from torch import autocast

from diffusers import StableDiffusionPipeline



pipe = StableDiffusionPipeline.from_pretrained(

	"CompVis/stable-diffusion-v1-4", 

	use_auth_token=True

).to("cuda")



prompt = "a photo of an astronaut riding a horse on mars"

with autocast("cuda"):

    image = pipe(prompt)["sample"][0]  

    

image.save("astronaut_rides_horse.png")

```



### Image Modification with Stable Diffusion



By using a diffusion-denoising mechanism as first proposed by [SDEdit](https://arxiv.org/abs/2108.01073), the model can be used for different 

tasks such as text-guided image-to-image translation and upscaling. Similar to the txt2img sampling script, 

we provide a script to perform image modification with Stable Diffusion.  



The following describes an example where a rough sketch made in [Pinta](https://www.pinta-project.com/) is converted into a detailed artwork.

```

python scripts/img2img.py --prompt "A fantasy landscape, trending on artstation" --init-img  --strength 0.8

```

Here, strength is a value between 0.0 and 1.0, that controls the amount of noise that is added to the input image. 

Values that approach 1.0 allow for lots of variations but will also produce images that are not semantically consistent with the input. See the following example.



**Input**



![sketch-in](assets/stable-samples/img2img/sketch-mountains-input.jpg)



**Outputs**



![out3](assets/stable-samples/img2img/mountains-3.png)

![out2](assets/stable-samples/img2img/mountains-2.png)



This procedure can, for example, also be used to upscale samples from the base model.



## Comments 



- Our codebase for the diffusion models builds heavily on [OpenAI's ADM codebase](https://github.com/openai/guided-diffusion)

and [https://github.com/lucidrains/denoising-diffusion-pytorch](https://github.com/lucidrains/denoising-diffusion-pytorch). 

Thanks for open-sourcing!



- The implementation of the transformer encoder is from [x-transformers](https://github.com/lucidrains/x-transformers) by [lucidrains](https://github.com/lucidrains?tab=repositories). 



## 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}

}

```