README.md

---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
datasets:
- Drozdik/tattoo_v3
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
    
# Text-to-image finetuning - TejasNavada/tattoo-diffusion

This pipeline was finetuned from **runwayml/stable-diffusion-v1-5** on the **Drozdik/tattoo_v3** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['a dragon on a white background', ' a fiery skull', 'a skull', 'a face', 'a snake and skull']: 

![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("TejasNavada/tattoo-diffusion", torch_dtype=torch.float16)
prompt = "a dragon on a white background"
image = pipeline(prompt).images[0]
image.save("my_image.png")
```

## Training info

These are the key hyperparameters used during training:

* Epochs: 100
* Learning rate: 5e-06
* Batch size: 2
* Image resolution: 512
* Mixed-precision: fp16