Update README.md
Browse files
README.md
CHANGED
|
@@ -55,8 +55,9 @@ Currently it is __NOT compatible with chaiNNer__, but will be available on the n
|
|
| 55 |
|
| 56 |
The `2x-AnimeSharpV4_Fast_RCAN_PU` model is trained on RCAN PixelUnshuffle. This is much faster, but comes at the cost of quality. I believe the model is ~95% the quality of the full V4 RCAN model, but ~6x faster in Pytorch and ~4x faster in TensorRT. This model is ideal for video processing, and as such was trained to handle MPEG2 & H264 compression.
|
| 57 |
|
| 58 |
-
To use the Pytorch version of the model right now, you can
|
| 59 |
|
|
|
|
| 60 |
__Comparisons:__
|
| 61 |
|
| 62 |
https://slow.pics/c/63Qu8HTN
|
|
|
|
| 55 |
|
| 56 |
The `2x-AnimeSharpV4_Fast_RCAN_PU` model is trained on RCAN PixelUnshuffle. This is much faster, but comes at the cost of quality. I believe the model is ~95% the quality of the full V4 RCAN model, but ~6x faster in Pytorch and ~4x faster in TensorRT. This model is ideal for video processing, and as such was trained to handle MPEG2 & H264 compression.
|
| 57 |
|
| 58 |
+
To use the Pytorch version of the model right now, you can update your version of the spandrel library to 0.4.1 in ComfyUI
|
| 59 |
|
| 60 |
+
Alternatively, the latest chaiNNer nightly supports it: https://github.com/chaiNNer-org/chaiNNer-nightly/releases
|
| 61 |
__Comparisons:__
|
| 62 |
|
| 63 |
https://slow.pics/c/63Qu8HTN
|