We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Motivation Please add support to convert more .pth files to .param for manga upscaling with apps like Upscayl.
Description When trying to convert .pth files like from here
https://github.com/the-database/MangaJaNai/releases/tag/1.0.0
or
https://openmodeldb.info/models/4x-IllustrationJaNai-V1-DAT2
in chaiNNer I get error messages like
`Error
An error occurred in a pytorch Convert To NCNN node:
Shape not currently supported by NCNN.
Input values: • PyTorch Model: Value of type 'spandrel.__helpers.model_descriptor.ImageModelDescriptor' • Data Type: fp32`
DAT is not supported for NCNN conversions at this time.
Alternatives Haven't found any alternative solutions or features.
Thank you.
The text was updated successfully, but these errors were encountered:
No branches or pull requests
Motivation
Please add support to convert more .pth files to .param for manga upscaling with apps like Upscayl.
Description
When trying to convert .pth files like from here
https://github.com/the-database/MangaJaNai/releases/tag/1.0.0
or
https://openmodeldb.info/models/4x-IllustrationJaNai-V1-DAT2
in chaiNNer I get error messages like
`Error
An error occurred in a pytorch Convert To NCNN node:
Shape not currently supported by NCNN.
Input values:
• PyTorch Model: Value of type 'spandrel.__helpers.model_descriptor.ImageModelDescriptor'
• Data Type: fp32`
or
`Error
An error occurred in a pytorch Convert To NCNN node:
DAT is not supported for NCNN conversions at this time.
Input values:
• PyTorch Model: Value of type 'spandrel.__helpers.model_descriptor.ImageModelDescriptor'
• Data Type: fp32`
Alternatives
Haven't found any alternative solutions or features.
Thank you.
The text was updated successfully, but these errors were encountered: