Won-Kyu Park
Won-Kyu Park
Please see https://github.com/wkpark/sd-webui-model-mixer/discussions/35
this routines are tensor level, it means it could be applied to the model-mixer easily. but also we need to check each algorthm and its meaning and it's speed.
yes. diffusers needed to use Lycoris/LoRA extractor. but diffusers dependency is not included in the `requirements.txt` or `install.py` for some reason. (diffusers used by many other webui-extensions but the versions...
part of issue resolved by commit 1701dd36a34bb88ca1d9fac65c8e192c8c4b1b0d
pick scorer_v1 + aesthetic_shadow_v2 scorers added. - aesthetic shadow ~ 4.3GB - pick scorer v1 ~ 3.7GB
did you try to use MBW mode? Internally, Auto merger helper utilizes MBW weights. (simple alpha weight will not work currently)
non MBW mode fixed now. thank you for your reporting
mbw mode with 7 hours? wow. I didn't do that much. all possible optimizers are not tested yet. some optimizer won't work at all. other optimizer will work as expected....
and 2-days ago, the following fix apply, https://github.com/wkpark/sd-webui-model-mixer/commit/d0710bd35a1fbc3beff9497ae21b06c25849e048 before this fix. merge process totally not work at all. please check your version before try to use auto merger
commit bb3808b was the regression bug. it prevents the merge from working properly. (I guess, that's why it fails to auto merge)