Kakigōri Maker

btw, model trained in unlocked mode could also be extracted as normal but it should pair with the original model to get intent/best result.

Looks good but maybe we should consider put this checkbox to batch tab only - for specific use (batch txt2img process).

Need to cleanup model loaders in annotator

Thanks for pointing out. Will implement some fix immediately

Fixed in https://github.com/Mikubill/sd-webui-controlnet/commit/b9efb602e5c6851e86d72d302e9592ddc0230d53, should work but still need some tests.

Hmm, looks like transferring control brings some instability. Temporary disabled and could be re-enable in the settings.

> I can make a pull request, and I also think you can easily copy the codes from there. Please feel free to modify it. Feel free to make a...

Merged. This method seems to be more correctly and effective. btw, any samples?

Difference models should be loaded without any issues. Feel free to open new issue if not works

maybe related: https://github.com/Mikubill/sd-webui-controlnet/issues/70