|
--- |
|
license: creativeml-openrail-m |
|
tags: |
|
- text-to-image |
|
- stable-diffusion |
|
language: |
|
- en |
|
library_name: diffusers |
|
pipeline_tag: text-to-image |
|
--- |
|
|
|
# Model Card: Stable-Cats-Generator |
|
|
|
## Model Information |
|
|
|
- **Model Name:** Stable-Cats-Generator |
|
- **Model Version:** v1 |
|
- **Model Type:** Image Generation |
|
- **Based on:** Stable Diffusion v2 |
|
|
|
 |
|
|
|
## Model Description |
|
|
|
Stable-Cats-Generator is an image generation model fine-tuned for generating white cat images based on text prompts. |
|
It is built upon **Stable Diffusion v2** and utilizes a pretrained text encoder (OpenCLIP-ViT/H) for text-to-image generation. |
|
**Stable Diffusion v2** is the latest version of the Stable Diffusion text-to-image diffusion model. |
|
It was released in 2023 and is based on the same core principles as the original Stable Diffusion model, but it has a number of improvements |
|
|
|
|
|
## Intended Use |
|
|
|
- Safe content generation |
|
- Artistic and creative processes |
|
- Bias and limitation exploration |
|
- Educational and creative tools |
|
|
|
## Potential Use Cases |
|
|
|
- Generating cat images for artistic purposes |
|
- Investigating biases and limitations of generative models |
|
- Creating safe and customizable content |
|
- Enhancing educational or creative tools |
|
|
|
## Model Capabilities |
|
|
|
- High-quality white cat image generation |
|
- Quick image generation, even on single GPUs |
|
- Customizable for specific needs and datasets |
|
|
|
## Limitations |
|
|
|
- May not always produce realistic images |
|
- Limited to generating white cat images based on text prompts |
|
- Ethical considerations when using generated content |
|
|
|
## Ethical Considerations |
|
|
|
- Ensure generated content is safe and non-harmful |
|
- Monitor and mitigate potential biases in generated content |
|
- Respect copyright and licensing when using generated images |
|
|
|
|
|
## Responsible AI |
|
|
|
- Ongoing monitoring and evaluation of model outputs |
|
- Regular updates to address limitations and improve safety |
|
- Compliance with ethical guidelines and legal regulations |
|
|
|
|
|
## Disclaimer |
|
|
|
This model card serves as a documentation tool and does not constitute legal or ethical guidance. Users of the model are responsible for adhering to ethical and legal standards in their use of the model. |
|
|
|
## Usage |
|
|
|
``` |
|
pip install diffusers==0.11.1 |
|
pip install transformers scipy ftfy accelerate |
|
``` |
|
```python |
|
import torch |
|
from diffusers import StableDiffusionPipeline |
|
|
|
pipe = StableDiffusionPipeline.from_pretrained("ayoubkirouane/Stable-Cats-Generator", torch_dtype=torch.float16) |
|
pipe = pipe.to("cuda") |
|
|
|
prompt = "A photo of a picture-perfect white cat." |
|
image = pipe(prompt).images[0] # image here is in [PIL format](https://pillow.readthedocs.io/en/stable/) |
|
|
|
# Now to display an image you can either save it such as: |
|
image.save(f"cat.png") |
|
|
|
# or if you're in a google colab you can directly display it with |
|
image |
|
|
|
``` |
|
|
