Hugging Face's logo

pszemraj
/
opt-350m-magicprompt-SD

Text Generation
Transformers
PyTorch
Safetensors
opt
Generated from Trainer
stable diffusion
diffusion
text2image
prompt augment
prompt engineering
Inference Endpoints
text-generation-inference
Model card Files Community
2
opt-350m-magicprompt-SD / README.md
pszemraj's picture
pszemraj
Update README.md
e7062c3
preview code
|
raw history blame
No virus
2.66 kB
metadata
license: other
tags:
  - generated_from_trainer
  - stable diffusion
  - diffusion
  - text2image
  - prompt augment
  - prompt engineering
datasets:
  - Gustavosta/Stable-Diffusion-Prompts
model-index:
  - name: opt-350m-magicprompt-SD
    results: []
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

opt-350m-magicprompt-SD

Generate/augment your prompt, stable diffusion style.

This model is a fine-tuned version of facebook/opt-350m on the Gustavosta/Stable-Diffusion-Prompts dataset. It achieves the following results on the evaluation set:

  • Loss: 1.2987
  • eval_steps_per_second = 16.623
  • perplexity = 3.6644

example

jakarta

output (on DALL-E 2, but as words are words, works anywhere)

dalle2-jakarta

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: 0.0001
  • train_batch_size: 8
  • eval_batch_size: 2
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 32
  • total_train_batch_size: 512
  • 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
2.8568 0.95 16 2.5937
2.2487 1.95 32 2.1050
1.9011 2.95 48 1.8082
1.6837 3.95 64 1.6178
1.4887 4.95 80 1.4897
1.3812 5.95 96 1.4017
1.2944 6.95 112 1.3437
1.2574 7.95 128 1.3127
1.2325 8.95 144 1.3009
1.2223 9.95 160 1.2987

Framework versions

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