City

That error doesn't seem to be caused by the code in this repo I don't think? The warning that seems noteworthy is defined [here](https://github.com/comfyanonymous/ComfyUI/blob/eecd69b53a896343775bcb02a4f8349e7442ffd1/comfy/sd.py#L230) and has to do with the...

Ah, you're also using the consistency decoder. I would recommend with sticking to the regular VAE [found here](https://huggingface.co/stabilityai/sd-vae-ft-mse-original) for 1.5 models. The consistency decoder is supported by this node pack,...

That seems to be a model to segment CT scans, if I'm reading it right? I don't think there's support for stuff like that in ComfyUI, since it's more of...

The only two models from that page that generate stuff are the "Brats mri axial slices generative diffusion" one, which only has brain MRI scans and "Mednist gan" [which is...

Sadly no, that model is meant for detecting (labeling) medical issues as far as I can tell.

Hmm, well Flan T5 is different from the T5 v1.1 version that PixArt alpha/sigma uses I'm pretty sure. Not to mention the XL vs XXL part. The current T5 linked...

I can add code to load it but there's no point without a model that actually expects embeddings from that text model. It's like trying to use clip_l (from sd1.5)...

@nighting0le01 The current code uses transformers, but I am planning on switching over to the comfy implementation of T5 as part of a bigger rewrite. Nothing gets loaded from huggingface,...

Just a hunch, but I think your transformers or pytorch version might be too old. I can't think of anything in my code that would end up with something on...

You might be able to upgrade those packages in your current env, assuming nothing else you use it for relies explicitly on the older versions. Can you paste the output...