|
--- |
|
license: creativeml-openrail-m |
|
tags: |
|
- pytorch |
|
- diffusers |
|
- stable-diffusion |
|
- text-to-image |
|
- diffusion-models-class |
|
--- |
|
# Dreambooth model of my cat azzy |
|
#### model by jefsnacker |
|
This is a Stable Diffusion model fine-tuned on pictures of Azriel with DreamBooth. |
|
It can be used by modifying the `instance_prompt`: **photo of azzy cat** |
|
|
|
This model was created as part of the DreamBooth Hackathon 🔥. Visit the [organization page](https://huggingface.co/dreambooth-hackathon) for instructions on how to take part! |
|
|
|
You can also train your own concepts and upload them to the library by using [this notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_training.ipynb). |
|
And you can run your new concept via `diffusers`: [Colab Notebook for Inference](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_inference.ipynb). |
|
|
|
## Sample Images |
|
12 images of Azriel were used to train the model. |
|
|
|
<table> |
|
<tr> |
|
<td align="center"><img src="https://huggingface.co/jefsnacker/azzy/resolve/main/concept_images/azzy00.jpg" style="height:200px"> </td> |
|
<td align="center"><img src="https://huggingface.co/jefsnacker/azzy/resolve/main/concept_images/azzy01.jpeg" style="height:200px"> </td> |
|
<td align="center"><img src="https://huggingface.co/jefsnacker/azzy/resolve/main/concept_images/azzy02.jpeg" style="height:200px"> </td> |
|
</tr> |
|
<tr> |
|
<td align="center"><img src="https://huggingface.co/jefsnacker/azzy/resolve/main/concept_images/azzy03.jpg" style="height:200px"> </td> |
|
<td align="center"><img src="https://huggingface.co/jefsnacker/azzy/resolve/main/concept_images/azzy04.jpg" style="height:200px"> </td> |
|
<td align="center"><img src="https://huggingface.co/jefsnacker/azzy/resolve/main/concept_images/azzy05.jpg" style="height:200px"> </td> |
|
</tr> |
|
<tr> |
|
<td align="center"><img src="https://huggingface.co/jefsnacker/azzy/resolve/main/concept_images/azzy06.jpeg" style="height:200px"> </td> |
|
<td align="center"><img src="https://huggingface.co/jefsnacker/azzy/resolve/main/concept_images/azzy07.jpeg" style="height:200px"> </td> |
|
<td align="center"><img src="https://huggingface.co/jefsnacker/azzy/resolve/main/concept_images/azzy08.jpeg" style="height:200px"> </td> |
|
</tr> |
|
<tr> |
|
<td align="center"><img src="https://huggingface.co/jefsnacker/azzy/resolve/main/concept_images/azzy09.jpeg" style="height:200px"> </td> |
|
<td align="center"><img src="https://huggingface.co/jefsnacker/azzy/resolve/main/concept_images/azzy10.jpeg" style="height:200px"> </td> |
|
<td align="center"><img src="https://huggingface.co/jefsnacker/azzy/resolve/main/concept_images/azzy11.jpeg" style="height:200px"> </td> |
|
</tr> |
|
</table> |
|
|
|
|
|
## Usage |
|
|
|
```python |
|
from diffusers import StableDiffusionPipeline, DPMSolverMultistepScheduler |
|
|
|
pipe = StableDiffusionPipeline.from_pretrained( |
|
"jefsnacker/azzy", |
|
scheduler = DPMSolverMultistepScheduler.from_pretrained("jefsnacker/azzy", subfolder="scheduler"), |
|
torch_dtype=torch.float16, |
|
).to("cuda") |
|
|
|
guidance_scale = 7 |
|
prompt = "Cute and adorable cartoon fluffy azzy cat with cap, with yellow eyes, fantasy, dreamlike, city scenario, surrealism, super cute, trending on artstation" #@param {type:"string"} |
|
|
|
images = pipe(prompt, num_images_per_prompt=1, num_inference_steps=50, guidance_scale=guidance_scale).images |
|
image[0] |
|
|
|
``` |
|
|
