---
license: apache-2.0
tags:
- generated_from_trainer
- stable diffusion
- diffusion
- text2image
- prompt augment
- prompt engineering
datasets:
- Gustavosta/Stable-Diffusion-Prompts
model-index:
- name: distilgpt2-magicprompt-SD
  results: []
thumbnail: https://i.ibb.co/WkmTnZD/image.png
widget:
 - text: "morning sun over Jakarta"
   example_title: "morning sun"
 - text: "WARNING: pip is"
   example_title: "pip"
 - text: "sentient cheese"
   example_title: "sentient cheese"
 - text: "cheeps are"
   example_title: "cheeps"
 - text: "avocado armchair"
   example_title: "creative prompt"
 - text: "Landscape of"
   example_title: "landscape"
parameters:
  min_length: 16
  max_new_tokens: 24
  no_repeat_ngram_size: 1
  do_sample: True
---

# distilgpt2-magicprompt-SD

[![colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/gist/pszemraj/bdddf9c3fe92d1ac2654730016d64c80/demo-distilgpt2-magicprompt.ipynb)

Generate/augment your prompt, stable diffusion style.

This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the Gustavosta/Stable-Diffusion-Prompts dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3089
- eval_steps_per_second   =     17.201
- perplexity              =     3.7022

## example


Results in (_DALL-E, but you get the idea_):

![example](https://i.ibb.co/WkmTnZD/image.png)


<br>

this `distilgpt2` version is probably small/fast enough to be used locally on CPU!

## basic usage

install transformers as needed:

```bash
pip install -U transformers
```

load and query through a `pipeline` object:

```python
from transformers import pipeline

model_tag = "pszemraj/distilgpt2-magicprompt-SD"
generator = pipeline(
    "text-generation",
    model=model_tag,
)

prompt = "The Answer to Why"
result = generator(
    prompt,
    max_new_tokens=24,
)  # generate, adjust/add kwargs as needed
print(result[0]["generated_text"])
```

## Training and evaluation data

refer to the `Gustavosta/Stable-Diffusion-Prompts` dataset.

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 16
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 10.0

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.7061        | 0.99  | 33   | 2.5859          |
| 2.08          | 1.99  | 66   | 1.9965          |
| 1.7623        | 2.99  | 99   | 1.7248          |
| 1.5408        | 3.99  | 132  | 1.5449          |
| 1.4147        | 4.99  | 165  | 1.4437          |
| 1.3593        | 5.99  | 198  | 1.3768          |
| 1.2703        | 6.99  | 231  | 1.3362          |
| 1.2528        | 7.99  | 264  | 1.3175          |
| 1.1981        | 8.99  | 297  | 1.3091          |
| 1.2117        | 9.99  | 330  | 1.3089          |


### Framework versions

- Transformers 4.25.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.6.1
- Tokenizers 0.13.1