Art-Prompter

A GPT powered predictive keyboard for making descriptive text prompts for A.I. image generators (e.g. MidJourney, Stable Diffusion, ArtBot, etc). The model was trained on a database of over 521K MidJourney images corresponding to 212K unique prompts.

Use the model through HuggingFace

from transformers import pipeline

ai = pipeline('text-generation',model='pearsonkyle/ArtPrompter', tokenizer='gpt2')

texts = ai('The', max_length=30, num_return_sequences=5)

for i in range(5):
    print(texts[i]['generated_text']+'\n')

Build prompts and generate images on Discord!

Examples

All text prompts below are generated with our language model and then evaluated with MidJourney v4

• The entire universe is a simulation,a confessional with a smiling guy fawkes mask, symmetrical, inviting,hyper realistic

• a pug disguised as a teacher. Setting is a class room

• I wish I had an angel For one moment of love I wish I had your angel Your Virgin Mary undone Im in love with my desire Burning angelwings to dust

• The heart of a galaxy, surrounded by stars, magnetic fields, big bang, cinestill 800T,black background, hyper detail, 8k, black

Training Setup

• Create a new virtual environment (e.g. conda create -n artprompt python=3.9)
• Activate the environment conda activate artprompt
• Install pytorch
  • conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia
• pip install transformers sqlalchemy sqlalchemy_utils pyuser_agent tqdm

Scrape MidJourney for prompts

1. Log in to browser and find cookie in request header
2. Set up sql database to store prompts.
   • python Database.py
3. Reproduce api call in python
4. Add unique entries to db
   • python midjourney_query.py

Train a language model

python train.py

Coming soon

• Interact with the prompter through a RESTFUL API hosted by a crowdsourced distributed cluster https://koboldai.net/