Giter Site home page Giter Site logo

structured-prompt-generator's Introduction

Structured Prompt Generator

with OpenAI GPT-3 Creations & Enhanced Prompt Writer

Made to construct well formed complex text prompts for Disco Diffusion and other text-to-image AI art platforms. This is a helper tool to create unique interesting descriptions in less time and visual surprises. 😎

Github Release version Open in Google Colab

  • Includes a comprehensive list of supported Artists and Styles
  • Start the sentence with a subject and let AI complete the scene with interesting details
  • Select which modifiers to apply to improve results, with list of positive and negative attributes
  • Use variables for random nouns, adjectives, colors, styles, and other useful terms in your creations
  • Generate prompt lists that can be used for batch image creations, animation timelines or other art making tools
  • Runs on Colab with CPU instead of GPU runtime, so you can play with it while you're Diffusing in other window

Credits:

https://colab.research.google.com/github/Skquark/structured-prompt-generator/blob/main/Structured_Prompt_Generator.ipynb


Enhanced Stable Diffusion 🎨

...using 🧨diffusers and practical bonus features...

  • Run a batch list of prompts at once, so queue many and walk away
  • Option to override any parameter per prompt in queue
  • Option to use Stability-API tokens for more samplers, bigger size & CPU runtime
  • Supports image2image use an init_image
  • Experimental prompt tweening to combine 2 prompts in a series
  • Can save all images to your Google Drive
  • Can Upscale automatically with Real-ESRGAN enlarging
  • Embeds exif metadata directly into png files
  • Disabled NSFW filtering and added custom sampler options
  • Renames image filenames to the prompt text, with options
  • Simple forms to set parameters, as easy as interactive python gets
  • OpenAI Prompt Generator and Noodle Soup Prompt Writer included
  • Standalone ESRGAN Upscaler for batch uploads and image splitting
  • Additional features added regularly...

https://colab.research.google.com/github/Skquark/structured-prompt-generator/blob/main/Enhanced_Stable_Diffusion_with_diffusers.ipynb


Enhanced DiscoArt 🎨

...Disco Diffusion /w Batch Prompts, Prompt Generators & SD init...

  • Easier Settings with GUI forms to give Parameters to DiscoArt creations
  • Saves image named with prompt, copies to GDrive, adds metadata, can save configs
  • Create Batch Prompts, listing as many complex prompts to process in queue
  • Override any of your default settings for any image in the batch list to allow experimentations
  • Integrated Stable Diffusion to Generate base init_image to Centipede to Disco pipeline
  • Can also generate higher quality init with Stability-API to use cheap tokens to save precious VRAM
  • Use OpenAI GPT-3 to Generate Prompts, give phase to start sentance, subject, AI adjustments, then generate away
  • Add random Artist & Styles, select +/- modifiers, custom weights, then generate lists in handy formats
  • Structured Prompt Writer to create your perfect prompts, supports Noodle Soup variables, custom modifiers and more
  • Convert standard prompt lists to new Json style, then add custom Prompt Schedualing and Clip Model Scheduler with helpers
  • Integrated Real-ESRGAN image upscaling with batch uploads or path, enlarge size scale, and GDrive upload option
  • and other extra touches you'll discover, with more Disco helpers to come...

https://colab.research.google.com/github/Skquark/structured-prompt-generator/blob/main/DiscoArt_%5B_w_Batch_Prompts_%26_GPT_3_Generator%5D.ipynb

structured-prompt-generator's People

Contributors

skquark avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

structured-prompt-generator's Issues

Request

Is there anyway to preserve faces when inpainting?

will clip guided diffusion ever support inpainting as well or is that a dumb question?

Thank you for saving me from Automatic1111

I wasn't able to run 1111 on my PC because of nvidia issues and I needed GFPGAN, ESRGAN, negative prompts and Euler...
Plus it runs on Jupyter Notebook and GPU servers without any problems.

You are a life saver. I wish I found your notebook earlier.
Star well deserved.

Now I can integrate it with my backend.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.