@daceheg192491 I updated yesterday due to getting black outputs with v2 int8, and is why I also tried the v3 fp8 version. I'm generating just fine with several other checkpoints.

just tried a barebones workflow and same issue, even tried the default clip/vae. bizarre... oh well, thanks anyway. :)

Same in webui forge neo with every version of this model; literally every other Krea2 checkpoint works fine :(

@sehrnaise7346865 Same situation.

@daceheg192491 @sehrnaise7346865 @rick3d I think I've figured out the problem.

diffusion models recently converted etc. (whatever the terms are) in ComfyUI no longer seem to be compatible with the Load Checkpoint node... model works fine after using Load Diffusion Model node. presumably forge neo is using what is essentially Load Checkpoint by default.

was having an issue with another model recently uploaded and changing node fixed my issues with both. which was a massive inconvenience, I had to move them to another folder!

@dow185 afaik the difference between the two is whether or not it loads a bundled VAE and CLIP encoder with the model.

@daceheg192491 did you bundle a VAE with your checkpoints by any chance?

@dow185 Are you aware of any fix when using forge neo?

@sehrnaise7346865 Updating forge neo and installing the Stable-yogi/sd-forge-int8-convrot extension also didn't help :(

@daceheg192491 Looking at the logs, I am actually already getting errors during model loading in webui. Maybe your combination of INT8 + BF16 that you mention is somehow not supported?

@schroeck there's an underlying .py file it's calling in order to load the model, so if you can switch out the file/change the code you could get it to work. I've used Grok for this sort of thing multiple times and it's been pretty good about it.

I expect this will get an official fix eventually, but it might happen on comfyui's end, in which case forge neo would simply not be able to use Models created (using comfyui?) during that time frame (unless there's an official, alternative loader that is equivalent to Load Diffusion Model).

I'm just a novice so I don't even know what I'm talking about - goodluck!

@schroeck remove yogi extension, it was quick hack before they added native support, what does you log say when you try to run it? have you tried switching in upper right corner of web ui diffusion from auto to bf16?

Same here with the black output. This is the only Krea2 checkpoint I have problem with SwarmUI.

Meanwhile the reason for some int8 quants not working (at least in ForgeNeo - appearently also SwarmUI) was found: If the file has int8 weights plus weight_scale but no quant-metadata (which Forge needs for MixedPrecision).

@Cyberdelia fixed it for his CyberRealistic models which had the same issue - quote "The issue was caused by the quantization metadata format, not the INT8 conversion itself."

Also @J1B fixed it and provided a new int8 version for his Krea2 Jib Mix checkpoints.

@daceheg192491 Would you consider the same? Thank you!

@daceheg192491 I created a node that you can use: https://github.com/cyberdeliaAI/ComfyUI-Cyberdelia-Quantizer

or PM me if you want a script that can fix your int8 without using the Comfyui node

@daceheg192491 Thank you! this version is working - mixed Precision all the way (and great merge!) Also thanks to @Cyberdelia for the guidance.