PromptGallery-stable-diffusion-webui

9.4 KiB

Raw Blame History

Prompt Gallery

A prompt cookbook worked as stable-diffusion-webui extenstions.
Watch Demo »

Explore the docs · Report Bug · Request Feature

Table of Contents

About The Project
- Built With
Getting Started
- Prerequisites
- Installation
Usage
Contributing
Contact
Acknowledgments

About The Project

TLDR; Stable-diffusion is an AI model which can generate illustration based on text-based prompts. What does a prompt/prompt-set in AI's eyes? How do we do prompt combination like shopping?

This is an extension of stable-diffusion-webui. Checkout this powerful tool.

Use Prompt Gallery like a cookbook. Build your own prompt-set library and do illustration/creation. Life is that easy.

Cool Features:

Scalable Prompt Library
Stable-Diffusion-WebUI Integration
Avatar System (model/character presets)

Keep your pace. Let's start from building your prompt library. Build Library

(back to top)

Built With

Gradio

(back to top)

Getting Started

Prerequisites

Clone Prompt-Gallery extension.

git clone https://github.com/dr413677671/PromptGallery-stable-diffusion-webui.git

Alternative-1) Download from github release

TBD

Alternative-2) Download from docker hub

TBD

Installation

Paste Prompt-Gallery in the root directory of stable-diffusion-webui.
Start ./webui-user.sh

If you see an error of missing library. Run

pip install -r <stable-diffusion-webui-path>/extensions/prompt-gallery/requirements.txt

(back to top)

Usage

View the video tutorial: View Demo

Build library

Build up the prompt library and character library.

value	negative	param
Positive prompts	Negative prompts	Other params of image generation

Edit the teamplate at /extensions/prompt-gallery/assets/avatars.yaml, and customize your avatars.

Teamplate:

 whiteHair: 
   value: "1 girl,  blush, White hair, Red eyes, animal ears,  looking at viewer, gothic lolita, dramatic angle, very beautiful, beautiful eyes, "
   negative: ""
 pinkGirl: 
   value: "petite, 1girl, solo, pink hair, very long hair, school uniform, happy,outdoors, flower field, excited"

Edit the teamplate at /extensions/prompt-gallery/assets/tags.yaml, and create your prompt-set categorical library.

Teamplate:

 Style:
   General Effect:
     "General_ice_high_res":
       value: "flowing ice, portrait, focus on face, complex, extremely detailed , elegant, CG, (an extremely delicate and beautiful girl), incredibly absurdres, best quality,concept art"
       negative: "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, "
       param: "Steps: 30, Sampler: Euler, CFG scale: 11.5, Seed: 1058629707, Size: 512x768, Variation seed: 1692844643, Variation seed strength: 0.27, Seed resize from: 1088x512"
 Background:
   '':
     simple background:
       value: simple background
     sunburst background:
       value: sunburst background
   Nature:
     Space:
       value: "space background, space,"
     Startrails:
       value: colorful startrails

Start stable-diffusion-webui

 ./webui-user.bat

Start Prompt Gallery

Slect tab "Prompt Gallery" on top navigation bar.

Select avatar (model for demo) -> Select prompt-sets -> Click "send WebUI"

Checkout the downloaded Images

Populate previews and QC

For instance having added two prompt-sets, and we would like to add preview pictures for them.

Goto tab "txt2img" and Select "Prompt Gallery" in tab "scripts"

Upload yaml library of avatar first and select avatar.

Add default prompts and upload prompt-set yaml library.

Wait for stable-diffusion-webui generate previews automatically.

Pick the best image for preview.

Check it out in Prompt Gallery.

(back to top)

Contributing

Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.

(back to top)