https://github.com/szymciem8/semantic-image-synthesis
Generative models that generate paintings in the style of Bob Ross based on segmentation images.
https://github.com/szymciem8/semantic-image-synthesis
fastapi gan gaugan machine-learning pix2pix spade streamlit tensorflow tensorflow2
Last synced: 8 months ago
JSON representation
Generative models that generate paintings in the style of Bob Ross based on segmentation images.
- Host: GitHub
- URL: https://github.com/szymciem8/semantic-image-synthesis
- Owner: szymciem8
- License: mit
- Created: 2022-12-26T21:22:10.000Z (almost 3 years ago)
- Default Branch: main
- Last Pushed: 2023-11-26T22:10:11.000Z (almost 2 years ago)
- Last Synced: 2025-01-08T12:11:06.234Z (9 months ago)
- Topics: fastapi, gan, gaugan, machine-learning, pix2pix, spade, streamlit, tensorflow, tensorflow2
- Language: Jupyter Notebook
- Homepage:
- Size: 88.8 MB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Semantic-Image-Synthesis


[](https://jupyter.org/try)## Bob Ross AI Painter
You can interact with the models through a Streamlit application.

The app is built with Docker. Use the command below to start the app locally.
```
docker-compose -f docker-compose.dev.yml up
```## Exmaples of GauGAN
Segmentation Map
Ground Truth
Generated Image
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
## Exmaples of Pix2Pix
Segmentation Map
Ground Truth
Generated Image
![]()
![]()
![]()