Get prompts/descriptions of images uploaded on discord.
Just join the touhouai discord, and click on PI-Chan's profile to see the "Add to Server" button. Click it and you'll invite it!
This Discord bot reacts to any image with generation metadata from the most/all popular webuis. (Create an issue if your favorite webui doesn't have it!) If you want to get a rough prompt (predicted with wdtagger), react with ❔
Install this if it breaks!
- Clone the repository
- Install the dependencies with
pip install -r requirements.txt
- Create a Discord bot and invite it to your server
- Enable the
Message Content Intent
in the Discord developer portal - Enable the
Server Members Intent
in the Discord developer portal - Copy/rename the
config.base.toml
intoconfig.toml
- Set
TOKEN = "<your discord bot token>"
in the .toml file - So like
TOKEN = "HFBVSAOa876vat764bq8967fgh8d8a76"
- Add the channel IDs you want the bot to work in into the
config.toml
file - Run the bot with
python3 PromptInspector.py
Webui | Supported? |
---|---|
Automatic 1111, sd.next, forge | ✅ |
ComfyUI | 🟨* |
Stable Swarm | ✅ |
NovelAI | ✅ |
Fooocus | ✅** |
*It returns the workflow and tries to extract the prompt, loras and checkpoints used
**Please test in TouhouAI, I think it will work though