Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
@@ -1,12 +1,55 @@
|
|
1 |
---
|
2 |
-
title:
|
3 |
-
emoji:
|
4 |
-
colorFrom:
|
5 |
-
colorTo:
|
6 |
sdk: gradio
|
7 |
-
sdk_version:
|
8 |
app_file: app.py
|
9 |
-
pinned:
|
|
|
10 |
---
|
11 |
|
12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
title: CCSR Upscaler
|
3 |
+
emoji: π
|
4 |
+
colorFrom: gray
|
5 |
+
colorTo: indigo
|
6 |
sdk: gradio
|
7 |
+
sdk_version: 3.23.0
|
8 |
app_file: app.py
|
9 |
+
pinned: true
|
10 |
+
short_description: Upscale an image using CCSR
|
11 |
---
|
12 |
|
13 |
+
# CCSR Upscaler
|
14 |
+
|
15 |
+
This Gradio space implements the Continuous Contrastive Super-Resolution (CCSR) model for image upscaling. CCSR is a state-of-the-art super-resolution method that can upscale images while preserving details and enhancing quality.
|
16 |
+
|
17 |
+
## Features
|
18 |
+
|
19 |
+
- Upload any image for upscaling
|
20 |
+
- Adjust super-resolution scale (1x to 8x)
|
21 |
+
- Fine-tune parameters like t_max and t_min
|
22 |
+
- Choose from different color fixing methods
|
23 |
+
|
24 |
+
## How to Use
|
25 |
+
|
26 |
+
1. Upload an image you want to upscale
|
27 |
+
2. Adjust the SR Scale slider to set the upscaling factor
|
28 |
+
3. Fine-tune t_max and t_min values if desired
|
29 |
+
4. Select a color fixing method from the dropdown
|
30 |
+
5. Click "Submit" to generate the upscaled image
|
31 |
+
|
32 |
+
## Model Details
|
33 |
+
|
34 |
+
This space uses the CCSR model trained on real-world images. The model checkpoint and configuration are loaded from:
|
35 |
+
|
36 |
+
- Checkpoint: `weights/real-world_ccsr.ckpt`
|
37 |
+
- Config: `configs/model/ccsr_stage2.yaml`
|
38 |
+
|
39 |
+
## Requirements
|
40 |
+
|
41 |
+
The main dependencies for this project are listed in the `requirements.txt` file, including:
|
42 |
+
|
43 |
+
- torch
|
44 |
+
- torchvision
|
45 |
+
- gradio
|
46 |
+
- einops
|
47 |
+
- pytorch-lightning
|
48 |
+
- omegaconf
|
49 |
+
- open-clip-torch
|
50 |
+
- xformers
|
51 |
+
- taming-transformers
|
52 |
+
|
53 |
+
## Acknowledgements
|
54 |
+
|
55 |
+
This implementation is based on the CCSR model. For more details about the original work, please refer to the [CCSR GitHub repository](https://github.com/camenduru/CCSR).
|