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
link NERVE-vs-HEART comparisons
Browse files
README.md
CHANGED
|
@@ -240,6 +240,11 @@ Rule of thumb: **HEART for maximum quality, NERVE for maximum practicality.**
|
|
| 240 |
Both export to dynamic ONNX; NERVE additionally converts to ncnn cleanly
|
| 241 |
because it has no attention ops.
|
| 242 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 243 |
---
|
| 244 |
|
| 245 |
## Repository layout
|
|
|
|
| 240 |
Both export to dynamic ONNX; NERVE additionally converts to ncnn cleanly
|
| 241 |
because it has no attention ops.
|
| 242 |
|
| 243 |
+
Side-by-side comparisons on the same real inputs (`input | bicubic | both
|
| 244 |
+
release models | both OTF GAN models`), with 1:1 crops: `examples/realphoto_nerve_vs_heart_compare.png`,
|
| 245 |
+
`examples/realphoto_nerve_vs_heart_1to1.png`, and the `noisy_*` versions.
|
| 246 |
+
|
| 247 |
+
|
| 248 |
---
|
| 249 |
|
| 250 |
## Repository layout
|