Won-Kyu Park

before gradio4 + flux supported version of forge was compatible with A1111 current version of the latest forge does not compatible with A1111 and the model-mixer at all.

> darn, can you recommend any alternatives that are compatible? recently, supermerger supports Flux + forge : https://github.com/hako-mikan/sd-webui-supermerger

> I was more interested in model mixer's ability to merge 5 models at once, can it do that? recently updated model-mixer support gradio4 but many parts of model-mixer does...

I guess you've open chrome/edge debugging console. forge is very laggy when using debugging console caused by too much noisy `console.warn` as already mentioned above. (and I guess, this is...

> The commit above fixes the error, thanks! > > Lora support seems incomplete, I don't know what key format is the current consensus (AFAIK there was at least one...

> Okay, a quick&dirty fix would be like this: > > ```diff > diff --git a/modules/models/flux/flux.py b/modules/models/flux/flux.py > index 46fd568a..f1f1cc72 100644 > --- a/modules/models/flux/flux.py > +++ b/modules/models/flux/flux.py > @@ -107,7...

> The latest commit breaks loading some SDXL models such as autismmix: `RuntimeError: Expected tensor for argument #1 'indices' to have one of the following scalar types: Long, Int; but...

> Getting `RuntimeError: "index_select_cuda" not implemented for 'Float8_e4m3fn'` when loading Flux-dev now. Torch version is 2.4.0. It loads fine with [edf4b9e](https://github.com/AUTOMATIC1111/stable-diffusion-webui/commit/edf4b9e94a4d1b747b93895f8da588639a84423b). something strange, if you don't mind let me know...

thank you for your reporting! I guess ffd15850 fix make some trouble for your environment. you can revert commit ffd15850 by `git revert ffd15850` command and see what you get.

I can reproduce your error with xformers optimization enabled case!