https://github.com/hansbug/sd_hcp

HCP-based stable diffusion image generator
https://github.com/hansbug/sd_hcp

Last synced: 5 months ago
JSON representation

HCP-based stable diffusion image generator

• Host: GitHub
• URL: https://github.com/hansbug/sd_hcp
• Owner: HansBug
• License: apache-2.0
• Created: 2024-02-27T11:24:33.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2024-02-28T13:11:19.000Z (over 2 years ago)
• Last Synced: 2024-12-29T15:10:15.617Z (over 1 year ago)
• Language: Python
• Size: 14.6 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# sd_hcp

HCP-based stable diffusion image generator

## Installation

```shell

git clone https://github.com/HansBug/sd_hcp.git

cd sd_hcp

pip install -r requirements.txt

make init

```

## T2I

```python

import matplotlib.pyplot as plt

from ditk import logging

from sd_hcp.infer import infer_images

logging.try_init_root(level=logging.INFO)

if __name__ == '__main__':

    images = infer_images(

        prompts=[

            'masterpiece, best quality, 1girl, solo, tohsaka rin, portrait',

        ],

        neg_prompts=[

            'lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry',

        ],

        seeds=[42],

    )

    plt.imshow(images[0])

    plt.show()

```