|
|
| --- |
| license: creativeml-openrail-m |
| base_model: CompVis/stable-diffusion-v1-4 |
| datasets: |
| - MaxReynolds/MyPatternDataset |
| tags: |
| - stable-diffusion |
| - stable-diffusion-diffusers |
| - text-to-image |
| - diffusers |
| inference: true |
| --- |
| |
| # Text-to-image finetuning - MaxReynolds/MyPatternModel |
| |
| This pipeline was finetuned from **CompVis/stable-diffusion-v1-4** on the **MaxReynolds/MyPatternDataset** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['<r4nd0m-l4b3l>']: |
|
|
|  |
|
|
|
|
| ## Pipeline usage |
|
|
| You can use the pipeline like so: |
|
|
| ```python |
| from diffusers import DiffusionPipeline |
| import torch |
| |
| pipeline = DiffusionPipeline.from_pretrained("MaxReynolds/MyPatternModel", torch_dtype=torch.float16) |
| prompt = "<r4nd0m-l4b3l>" |
| image = pipeline(prompt).images[0] |
| image.save("my_image.png") |
| ``` |
|
|
| ## Training info |
|
|
| These are the key hyperparameters used during training: |
|
|
| * Epochs: 25 |
| * Learning rate: 1e-05 |
| * Batch size: 1 |
| * Gradient accumulation steps: 4 |
| * Image resolution: 512 |
| * Mixed-precision: fp16 |
|
|
|
|
| More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/max-f-reynolds/text2image-fine-tune/runs/vc3btybi). |
|
|
