Image-to-Image
PyTorch
ONNX
TensorRT
English
super-resolution
image-restoration
sisr
real-world-restoration
spandrel
chainner
transformer
attention
Instructions to use Phips/HEART with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TensorRT
How to use Phips/HEART with TensorRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
document 1:1 crops + inputs
Browse files
README.md
CHANGED
|
@@ -176,9 +176,12 @@ All ONNX files are **dynamic-shape fp32, opset 17, onnxslim-optimized**.
|
|
| 176 |
`examples/inputs/` also contains the original Real-ESRGAN test images, so you
|
| 177 |
can inspect full-size inputs and run the models yourself.
|
| 178 |
|
| 179 |
-
A second set
|
| 180 |
-
|
| 181 |
-
|
|
|
|
|
|
|
|
|
|
| 182 |
|
| 183 |
---
|
| 184 |
|
|
|
|
| 176 |
`examples/inputs/` also contains the original Real-ESRGAN test images, so you
|
| 177 |
can inspect full-size inputs and run the models yourself.
|
| 178 |
|
| 179 |
+
A second set (`realphoto`, `ani`, `manga`, `text`, `noisy`, `stablediffusion`)
|
| 180 |
+
feeds real images in **as-is** (not downscaled):
|
| 181 |
+
- `examples/*_compare.png` — whole image: **input** | **bicubic x4** |
|
| 182 |
+
**HEART 4x release** | **HEART 4x OTF GAN**.
|
| 183 |
+
- `examples/*_1to1.png` — a **1:1 native-pixel center crop** (detail comparison).
|
| 184 |
+
The source inputs are in `examples/inputs/`.
|
| 185 |
|
| 186 |
---
|
| 187 |
|