|
|
|
--- |
|
license: creativeml-openrail-m |
|
base_model: OFA-Sys/small-stable-diffusion-v0 |
|
datasets: |
|
- jwl25b/final_project_dataset |
|
tags: |
|
- stable-diffusion |
|
- stable-diffusion-diffusers |
|
- text-to-image |
|
- diffusers |
|
inference: true |
|
--- |
|
|
|
# Text-to-image finetuning - arpachat/small-stable-diffusion-v0-th-200 |
|
|
|
This pipeline was finetuned from **OFA-Sys/small-stable-diffusion-v0** on the **jwl25b/final_project_dataset** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ["Tommy Hilfiger men's Regular Fit Round Logo Grey Polo"]: |
|
|
|
![val_imgs_grid](./val_imgs_grid.png) |
|
|
|
|
|
## Pipeline usage |
|
|
|
You can use the pipeline like so: |
|
|
|
```python |
|
from diffusers import DiffusionPipeline |
|
import torch |
|
|
|
pipeline = DiffusionPipeline.from_pretrained("arpachat/small-stable-diffusion-v0-th-200", torch_dtype=torch.float16) |
|
prompt = "Tommy Hilfiger men's Regular Fit Round Logo Grey Polo" |
|
image = pipeline(prompt).images[0] |
|
image.save("my_image.png") |
|
``` |
|
|
|
## Training info |
|
|
|
These are the key hyperparameters used during training: |
|
|
|
* Epochs: 100 |
|
* Learning rate: 1e-05 |
|
* Batch size: 8 |
|
* 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](wandb_run_url). |
|
|