Skip to content

kumeS/stableDiffusion4R

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

stableDiffusion4R

GitHub/stableDiffusion4R

Description

Artificial Intelligence (AI)-based image generation techniques are revolutionizing various fields, and this package brings those capabilities into the R environment. This package provides a seamless interface to integrate the 'Stable Diffusion' Web APIs (see https://platform.stability.ai/docs/getting-started) into R, allowing users to leverage advanced image transformation methods. Specifically, this package includes functions for text-to-image (txt2img or t2i) and image-to-image (img2img or i2i) transformations using the 'Stable Diffusion' APIs, enabling creative and analytical applications in data visualization and more.

This package was separated from the chatAI4R project.

About this project

Installation of the stableDiffusion4R package

1. Start R / RStudio console.

2. Run the following commands in the R console:

CRAN-version installation

# CRAN-version installation (not yet)
install.packages("BiocManager", repos="http://cran.r-project.org")
BiocManager::install("EBImage")

#install.packages("stableDiffusion4R")
#library(stableDiffusion4R)

Dev-version installation (Recommended)

# Dev-version installation
install.packages(c("devtools", "BiocManager"), repos="http://cran.r-project.org")
BiocManager::install("EBImage")

devtools::install_github("kumeS/stableDiffusion4R")
library(stableDiffusion4R)

3. Set the API Key According to each Web API

For example, to obtain a DreamStudio API key, please register as a member on the DreamStudio website (https://dreamstudio.ai/generate) and obtain your API key.

# Set your key for the DreamStudio API
Sys.setenv(DreamStudio_API_KEY = "Your API key")

Create an .Rprofile file in your home directory and add your API key (using the code above) into it.

# Create a file
file.create("~/.Rprofile") 

# [MacOS X] Open the file and edit it
system(paste("open ~/.Rprofile"))

Note: Please be aware of newline character inconsistencies across different operating systems.

Prompts for chatGPT / GPT-4

File Description Prompt
A prompt to analyze themes for unified imagery Prompt

R Functions

Image generation functions using Stable Diffusion

Function Description Script Flowchart
txt2img4R Text-to-image generator using Stable Diffusion Script
img2img4R Image to Image Transformation using Stable Diffusion Script
img2img_upscale4R Stable Diffusion Image to Image Up-scaling Transformation Script

Task specific image generation

Image generation functions using DALL·E 2

Function Description Script Flowchart
generateImage4R Generate Images Using OpenAI API Script
editImage4R Edit or Extend Images with OpenAI API Script
imageVariation4R Generate Image Variations using OpenAI API Script
createImagePrompt_v1 create a prompt for generating an image from text using an AI model Script
createImagePrompt_v2 create a more complex prompt by considering additional attributes Script

Visualization functions

Function Description Script Flowchart
Display Display images and optionally write them into image files Script
createHEX Create Hex Stickers for R Packages (experimental) Script Flowchart

Visualization functions

Function Description Script Flowchart
imgDisplay Display images and optionally write them into image files Script
imgDisplayAsMovie Display Images as a Movie Script

License

Copyright (c) 2023 Satoshi Kume. Released under the Artistic License 2.0.

Cite

Kume S. (2023) stableDiffusion4R: R Interface to 'Stable Diffusion' APIs for AI-Driven Creative Image Transformations

#BibTeX
@misc{Kume2023stableDiffusion4R,
  title={stableDiffusion4R: R Interface to 'Stable Diffusion' APIs for AI-Driven Creative Image Transformations},
  author={Kume, Satoshi}, year={2023},
  publisher={GitHub}, note={R Package},
  howpublished={\url{https://github.com/kumeS/stableDiffusion4R}},
}

Contributors

  • Satoshi Kume

Releases

No releases published

Packages

No packages published

Languages