Allow ESRGAN models to run with 1x and 8x scale #10
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Owner
|
Thanks, wasn't aware of those. I noticed when running the 8x model that GPU/Vulkan has issues when resolution gets too large (eg. target resolution 1536x1536 from default tile size 224). Image looks garbled. It's a general issue with the convolution kernel, will take some time to fix it. Smaller tile size can be used as a workaround. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR allows running ESRGAN models with 1x and 8x scale.
For example 1x-NMKD-Jaywreck3-Lite and 8x_NMKD-Superscale_150000_G.
Both models run after this change, and results for the 1x model are promising.