Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,40 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
|
| 4 |
+
tags:
|
| 5 |
+
- gan
|
| 6 |
+
- unconditional image generation
|
| 7 |
+
- huggan
|
| 8 |
+
- style-transfer
|
| 9 |
+
- cyclegan
|
| 10 |
+
- Pytorch
|
| 11 |
+
|
| 12 |
+
|
| 13 |
---
|
| 14 |
+
|
| 15 |
+
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.
|
| 16 |
+
|
| 17 |
+
## Dataset
|
| 18 |
+
|
| 19 |
+
The model is trained on 256x256 high contrasted neon images as style images, and normal images (including people,scenery etc.) as base images.
|
| 20 |
+
|
| 21 |
+
### Dataset - https://www.kaggle.com/datasets/aanisha07/futuristic-images
|
| 22 |
+
|
| 23 |
+
## Model
|
| 24 |
+
|
| 25 |
+
All details regarding how to use the model, fine-tune it, are added to GitHub.
|
| 26 |
+
|
| 27 |
+
### Github - https://github.com/Aanisha/NeonGAN
|
| 28 |
+
|
| 29 |
+
## Demo
|
| 30 |
+
|
| 31 |
+
Check out the spaces demo, and try the model by yourselves.
|
| 32 |
+
|
| 33 |
+
### Demo - https://huggingface.co/spaces/huggan/NeonGAN_Demo
|
| 34 |
+
|
| 35 |
+
Hope you all enjoy it!
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
|