|
|
--- |
|
|
license: mit |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: ArtPrompter |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# [ArtPrompter](https://pearsonkyle.github.io/Art-Prompter/) |
|
|
|
|
|
A [gpt2](https://huggingface.co/gpt2) 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 268K MidJourney images corresponding to 113K unique prompts. |
|
|
|
|
|
```python |
|
|
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') |
|
|
``` |
|
|
|
|
|
[](https://colab.research.google.com/drive/1HQOtD2LENTeXEaxHUfIhDKUaPIGd6oTR?usp=sharing) |
|
|
|
|
|
|
|
|
## Intended uses & limitations |
|
|
|
|
|
Build prompts and generate images on Discord! |
|
|
|
|
|
|
|
|
[](https://discord.gg/3S8Taqa2Xy) |
|
|
|
|
|
|
|
|
[](https://discord.gg/3S8Taqa2Xy) |
|
|
|
|
|
|
|
|
|
|
|
## Examples |
|
|
|
|
|
All text prompts below are generated with our language model |
|
|
|
|
|
- *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 procedure |
|
|
|
|
|
~1 hour of finetuneing on RTX2080 with 113K unique prompts |
|
|
|
|
|
### Training hyperparameters |
|
|
|
|
|
The following hyperparameters were used during training: |
|
|
- learning_rate: 5e-05 |
|
|
- train_batch_size: 16 |
|
|
- eval_batch_size: 4 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 50 |
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.25.1 |
|
|
- Pytorch 1.13.1 |
|
|
- Tokenizers 0.13.2 |
|
|
|
