Ilja Razinkov

Hard to tell (not using them, so never looked into it). looking at code there is suspicious lora parsing in "match_lora" method in core.py. Possibly DORA have some unexpected internal...

> I added it locally and it worked for me!! DORAs work properly now!! > I would push it to this branch but I cannot since I don't have edit...

> Here it is: Thanks! Pushed it to the branch - https://github.com/IPv6/Fooocus4BL/commit/1157a1df68e005568c0f449e278042833cea6485

> Sorry for the newbie question, but how do I use a branch instead of the main repository? Specifically in Google Collab. Don`t know regarding colab, but for using branch...

> called "--always-high-vram". What it does is to better manage memory This param was changed in Comfy, so updated ldm require new setting instead of old one. try --highvram --use-pytorch-cross-attention...

> Any idea how hard it would be to add support for SD3.5? Would be as difficult as adding the DORA support? Or far higher? SD3.5 has different architecture comparing...

> Is there any way to avoid this and do everything in one request without crutches? Currently NO, the internals has a lot of shared state, afaik you can run...

Also hit similar problem - some scheduler/sampler pairs always produce black images on M3 - and thankfully same problem was with Comfy and same solution helped me. It is "--force-upcast-attention"...

RuniedFooocus have an option to directly use comfyUI behind the scenes, without throughout deep integration with other features. Cool, but... it`s not a Fooocus way, imho

Try "--force-upcast-attention" command line option, Comfy have similar problems on MacOs M*