Add links to paper, code, and project page
Browse filesThis PR makes the existing resources easier to find by pointing the `Paper` badge to the actual Hugging Face paper page and adding explicit links to the project page and GitHub repository. The existing metadata and tags are kept unchanged because they already cover the model license, pipeline, and topic appropriately.
README.md
CHANGED
|
@@ -1,16 +1,16 @@
|
|
| 1 |
---
|
| 2 |
-
license: cc-by-nc-4.0
|
| 3 |
base_model: stabilityai/stable-diffusion-3-medium-diffusers
|
| 4 |
-
pipeline_tag: image-to-image
|
| 5 |
language: en
|
|
|
|
|
|
|
| 6 |
tags:
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
---
|
| 15 |
|
| 16 |
# OracleZoom
|
|
@@ -19,14 +19,18 @@ tags:
|
|
| 19 |
|
| 20 |
\*Equal contribution.
|
| 21 |
|
| 22 |
-
**Privileged-Latent Distillation for faithful extreme super-resolution.**
|
| 23 |
OracleZoom drives Chain-of-Zoom's recursive 4x super-resolution out to 256x while staying *faithful*, adding real detail instead of hallucinating. **This repo is self-contained**: the merged model, the inference code, and the required checkpoints are all here. You only download two public base models (Stable Diffusion 3-medium, Qwen2.5-VL-3B) automatically.
|
| 24 |
|
| 25 |
-
[](https://huggingface.co/stabilityai/stable-diffusion-3-medium-diffusers)
|
| 26 |
-
[](https://github.com/bryanswkim/Chain-of-Zoom)
|
| 27 |
-
[-red)](
|
|
|
|
|
|
|
| 28 |
[](https://creativecommons.org/licenses/by-nc/4.0/)
|
| 29 |
|
|
|
|
|
|
|
| 30 |
## Quickstart (one image, all scales)
|
| 31 |
|
| 32 |
Needs one NVIDIA GPU (~16 GB) and Python 3.10.
|
|
@@ -101,4 +105,4 @@ The `coz/` code and the checkpoints in `ckpt/` are from [Chain-of-Zoom](https://
|
|
| 101 |
note={In submission, WACV 2026}
|
| 102 |
}
|
| 103 |
```
|
| 104 |
-
Please also cite Chain-of-Zoom and OSEDiff.
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
base_model: stabilityai/stable-diffusion-3-medium-diffusers
|
|
|
|
| 3 |
language: en
|
| 4 |
+
license: cc-by-nc-4.0
|
| 5 |
+
pipeline_tag: image-to-image
|
| 6 |
tags:
|
| 7 |
+
- super-resolution
|
| 8 |
+
- image-super-resolution
|
| 9 |
+
- extreme-zoom
|
| 10 |
+
- chain-of-zoom
|
| 11 |
+
- diffusion
|
| 12 |
+
- privileged-distillation
|
| 13 |
+
- faithfulness
|
| 14 |
---
|
| 15 |
|
| 16 |
# OracleZoom
|
|
|
|
| 19 |
|
| 20 |
\*Equal contribution.
|
| 21 |
|
| 22 |
+
**Privileged-Latent Distillation for faithful extreme super-resolution.**
|
| 23 |
OracleZoom drives Chain-of-Zoom's recursive 4x super-resolution out to 256x while staying *faithful*, adding real detail instead of hallucinating. **This repo is self-contained**: the merged model, the inference code, and the required checkpoints are all here. You only download two public base models (Stable Diffusion 3-medium, Qwen2.5-VL-3B) automatically.
|
| 24 |
|
| 25 |
+
[](https://huggingface.co/stabilityai/stable-diffusion-3-medium-diffusers)
|
| 26 |
+
[](https://github.com/bryanswkim/Chain-of-Zoom)
|
| 27 |
+
[-red)](https://huggingface.co/papers/2609.06490)
|
| 28 |
+
[](https://github.com/dipta007/OracleZoom)
|
| 29 |
+
[](https://dipta007.github.io/OracleZoom/)
|
| 30 |
[](https://creativecommons.org/licenses/by-nc/4.0/)
|
| 31 |
|
| 32 |
+
**Paper:** https://huggingface.co/papers/2609.06490 路 **Code:** https://github.com/dipta007/OracleZoom 路 **Project page:** https://dipta007.github.io/OracleZoom/
|
| 33 |
+
|
| 34 |
## Quickstart (one image, all scales)
|
| 35 |
|
| 36 |
Needs one NVIDIA GPU (~16 GB) and Python 3.10.
|
|
|
|
| 105 |
note={In submission, WACV 2026}
|
| 106 |
}
|
| 107 |
```
|
| 108 |
+
Please also cite Chain-of-Zoom and OSEDiff.
|