|
--- |
|
license: creativeml-openrail-m |
|
tags: |
|
- pytorch |
|
- diffusers |
|
- stable-diffusion |
|
- text-to-image |
|
- keyboard |
|
widget: |
|
- text: a photo of cyberboard keyboard |
|
datasets: |
|
- li-yan/crazy-keyboard |
|
--- |
|
|
|
<center> |
|
|
|
![crazy-keyboard](https://huggingface.co/li-yan/stable-diffusion-crazy-keyboard/resolve/main/docs/crazy-keyboard.gif) |
|
|
|
</center> |
|
|
|
Are you a fan of keyboards? Above is my Cyberboard Keyboard that I used for my dialy life. **It is crazy right?** |
|
|
|
![crazy-keyboard](https://huggingface.co/li-yan/stable-diffusion-crazy-keyboard/resolve/main/docs/am-cb-r4.gif) |
|
|
|
Now I bring this keyboard into the Stable Diffusion, and its images can be generate by the model. |
|
|
|
## Description |
|
|
|
This is a Stable Diffusion model fine-tuned on dataset [li-yan/crazy-keyboard](https://huggingface.co/datasets/li-yan/crazy-keyboard) images. |
|
|
|
#### Prompt 1: "a photo of cyberboard keyboard" |
|
| ![image-fine-tuned-1](https://huggingface.co/li-yan/stable-diffusion-crazy-keyboard/resolve/main/docs/generated/pretrained-prompt1.png) | ![image-fine-tuned-1](https://huggingface.co/li-yan/stable-diffusion-crazy-keyboard/resolve/main/docs/generated/fine-tuned-prompt1.png) | |
|
|:--:|:--:| |
|
| result of pretrained model | result of fine tuned model | |
|
|
|
#### Prompt 2: "in the forest, a cyberboard keyboard is on the ground" |
|
| ![image-fine-tuned-1](https://huggingface.co/li-yan/stable-diffusion-crazy-keyboard/resolve/main/docs/generated/pretrained-prompt2.png) | ![image-fine-tuned-1](https://huggingface.co/li-yan/stable-diffusion-crazy-keyboard/resolve/main/docs/generated/fine-tuned-prompt2.png) | |
|
|:--:|:--:| |
|
| result of pretrained model | result of fine tuned model | |
|
|
|
#### Prompt 3: "a cyberboard keyboard in front of the Golden Gate Bright" |
|
| ![image-fine-tuned-1](https://huggingface.co/li-yan/stable-diffusion-crazy-keyboard/resolve/main/docs/generated/pretrained-prompt3.png) | ![image-fine-tuned-1](https://huggingface.co/li-yan/stable-diffusion-crazy-keyboard/resolve/main/docs/generated/fine-tuned-prompt3.png) | |
|
|:--:|:--:| |
|
| result of pretrained model | result of fine tuned model | |
|
|
|
|
|
# Details |
|
|
|
Trained by li-yan on the [li-yan/crazy-keyboard](li-yan/crazy-keyboard) dataset. |
|
|
|
This model is fine tuned from pretrained model [CompVis/stable-diffusion-v1-4](https://huggingface.co/CompVis/stable-diffusion-v1-4) using DreamBooth model. |
|
|
|
More for DreamBooth model, please refer to https://dreambooth.github.io/. |
|
|
|
## Usage |
|
|
|
```python |
|
pip install -qqU diffusers accelerate |
|
|
|
import torch |
|
from diffusers import StableDiffusionPipeline |
|
|
|
pipe = StableDiffusionPipeline.from_pretrained("li-yan/stable-diffusion-crazy-keyboard") |
|
|
|
# set prompt |
|
prompt = "a photo of cyberboard keyboard" #@param |
|
guidance_scale=12 #@param {type:"integer"} |
|
num_inference_steps = 50 #@param {type:"integer"} |
|
|
|
# Run the pipeline, showing some of the available arguments |
|
pipe_output = pipe( |
|
prompt=prompt, # What to generate |
|
negative_prompt="Oversaturated, blurry, low quality", # What NOT to generate |
|
height=480, width=640, # Specify the image size |
|
guidance_scale=guidance_scale, # How strongly to follow the prompt |
|
num_inference_steps=num_inference_steps, # How many steps to take |
|
) |
|
|
|
# View the resulting image |
|
pipe_output.images[0] |
|
``` |
|
|
|
## Fine Tune Source Code |
|
[<img src="https://colab.research.google.com/assets/colab-badge.svg">](https://colab.research.google.com/github/Li-Yan/Diffusion-Model/blob/main/Li_Yan_Stable_Defussion_Fune_Tuning.ipynb) |