-
Notifications
You must be signed in to change notification settings - Fork 385
New issue
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
Tile model training details #69
Comments
I also have really big curiousity about how to train tiling model. is it similar to IF method? there are, I think, other different upscaling methods for getting clear, sharpt high resolution images like IF, SD x4 upscaler, SDXL 0.9(1.0 soon). I tried to img2img on SD x4 upscaler and Controlnet tile model and I think your model wins. what is the difference? how to prepare dataset for retraining? should I have 4K image and reduce the size and apply several blurring? that's all? then Controlnet will output bigger sized images while training? |
@dedoogong what is IF method? |
DeepFloyd IF (Imagen) |
Any new information about this topic? |
also see #125 |
In case anyone is still interested, I got controlnet tile training working, and the script is uploaded here https://github.com/zjysteven/controlnet_tile. |
Could you please provide details on what data you used to train a tile model. Were it crops from big images? Did you use down-up resampling? And some other information.
The text was updated successfully, but these errors were encountered: