Hugging Face's logo

pszemraj
/
opt-350m-multiprompt

Text Generation
Transformers
PyTorch
Safetensors
opt
Generated from Trainer
text generation
stable diffusion
midjourney
text2image
text to image
prompt augment
prompt engineering
Inference Endpoints
text-generation-inference
Model card Files Community
2
opt-350m-multiprompt / README.md
pszemraj's picture
pszemraj
Update README.md
b81b2f1
preview code
|
raw history blame contribute delete
No virus
2.94 kB
metadata
license: other
tags:
  - generated_from_trainer
  - text generation
  - stable diffusion
  - midjourney
  - text2image
  - text to image
  - prompt augment
  - prompt engineering
thumbnail: https://i.imgur.com/DeKNHtC.jpg
datasets:
  - pszemraj/text2image-multi-prompt
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_length: 96
  no_repeat_ngram_size: 1
  do_sample: true

pszemraj/opt-350m-multiprompt

Open In Colab

Generate/augment your prompt with a model trained on a large & diverse prompt dataset.

This model is a fine-tuned version of facebook/opt-350m on the pszemraj/text2image-prompts-multi dataset. It achieves the following results on the evaluation set:

  • Loss: 1.6669
  • eval steps per second: 16.21
  • perplexity: 5.29

Example

landscape of florida


The above example was created with DALL-E 2 but will of course work with any text2image model.

Intended uses & limitations

  • The model will generate augmentations that are biased towards the training data, i.e. what people already asked for in the SD/midjourney discords, etc. Creating a larger dataset was an attempt at mitigating this through more data from different datasets.

Training and evaluation data

See the pszemraj/text2image-prompts-multi dataset card for details. The dataset is a compilation of several text-to-image prompt datasets on huggingface :)

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0002
  • train_batch_size: 8
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 256
  • total_eval_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.04
  • num_epochs: 4.0

Training results

Training Loss Epoch Step Validation Loss
2.1677 1.0 990 2.0888
1.856 2.0 1980 1.8215
1.6864 3.0 2970 1.6935
1.6228 4.0 3960 1.6670

Framework versions

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