|
--- |
|
license: mit |
|
|
|
tags: |
|
- gan |
|
- unconditional image generation |
|
- huggan |
|
- style-transfer |
|
- cyclegan |
|
- Pytorch |
|
- unconditional-image-generation |
|
|
|
|
|
--- |
|
|
|
This model is based on [CycleGAN](https://arxiv.org/abs/1703.10593) architecture. It takes images, and generates a futuristic neon image for the image provided.Hope this model neonifies your images. |
|
 |
|
|
|
# Dataset |
|
|
|
The model is trained on 256x256 high contrasted neon images as style images, and normal images (including people,scenery etc.) as base images. |
|
|
|
#### Dataset - https://www.kaggle.com/datasets/aanisha07/futuristic-images |
|
|
|
# Model |
|
|
|
All details regarding how to use the model, fine-tune it, are added to GitHub. |
|
|
|
#### Github - https://github.com/Aanisha/NeonGAN |
|
|
|
# Spaces Demo |
|
|
|
Check out the spaces demo, and try the model by yourselves. |
|
|
|
#### Demo - https://huggingface.co/spaces/huggan/NeonGAN_Demo |
|
|
|
|
|
|
|
Hope you all enjoy it! |
|
|
|
|
|
|
|
|
|
|
|
|
