search

arenasys / stable-diffusion-webui-model-toolkit

A Multipurpose toolkit for managing, editing and creating models.
MIT License
508 stars 34 forks source link

[help] Model is 1.60 GB. Model type identified as UNET-v1-BROKEN. Model components are: UNET-v1-SD. #40

Open zethfoxster opened 1 year ago

zethfoxster commented 1 year ago

I know you can replace a vae, but is there any way to fix this?

Samael-1976 commented 1 year ago

same problem here!

zethfoxster commented 1 year ago

a solution is to combine a model that has a working unet at a very very small ratio as model A...and this as model broken one at model B....it keeps the working unet

QinCaii commented 1 year ago

same here, The training script does not require a vae to be merged, and each checkpoint is BROKEN after the training, I wonder how this came about.

arenasys commented 1 year ago

Im guessing its a checkpoint that only contains a UNET, If thats the case you need to get a VAE and CLIP from an intact checkpoint.

Load the intact checkpoint, then import the UNET from your broken checkpoint, then save it under a new name. (Similar procedure to replacing a VAE, but its the UNET). Should work.

QinCaii commented 1 year ago

Im guessing its a checkpoint that only contains a UNET, If thats the case you need to get a VAE and CLIP from an intact checkpoint.

Load the intact checkpoint, then import the UNET from your broken checkpoint, then save it under a new name. (Similar procedure to replacing a VAE, but its the UNET). Should work.

Your suggestion is correct, I got UNET and VAE from the checkpoint after training instead of using the VAE from base model, but it still works.

QinCaii commented 1 year ago

Whether using VAE in the base model or the BROKEN checkpoint, the final result has the same hash value. So.. maybe it didn't include a VAE