Image-to-Image
PyTorch
ONNX
TensorRT
English
super-resolution
image-restoration
sisr
onnxruntime
spandrel
chainner
edge
deployment
mit
Instructions to use Phips/PULSE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TensorRT
How to use Phips/PULSE 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
Position PULSE against NERVE
Browse files
PAPER.md
CHANGED
|
@@ -79,8 +79,12 @@ be a component, but flicker-free video needs temporal conditioning.
|
|
| 79 |
| Text/UI/screenshot upscaling | a text-aware restoration model, not PULSE |
|
| 80 |
| Temporal video restoration | a temporal model; PULSE is per-frame only |
|
| 81 |
|
| 82 |
-
PULSE is
|
| 83 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84 |
|
| 85 |
## Pick a model
|
| 86 |
|
|
|
|
| 79 |
| Text/UI/screenshot upscaling | a text-aware restoration model, not PULSE |
|
| 80 |
| Temporal video restoration | a temporal model; PULSE is per-frame only |
|
| 81 |
|
| 82 |
+
PULSE is the **tiny/fast NERVE sibling**: the same practical philosophy, but
|
| 83 |
+
far fewer parameters and a lighter operating envelope. NERVE is the more
|
| 84 |
+
capable restoration model; PULSE is for light degradation, clean upscaling,
|
| 85 |
+
browser/CPU use, and cases where the model itself must be almost free.
|
| 86 |
+
|
| 87 |
+
PULSE is not competing with HEART on PSNR.
|
| 88 |
|
| 89 |
## Pick a model
|
| 90 |
|