InvokeAI
InvokeAI copied to clipboard
[bug]: SDXL Lightning model installs as VAE
Is there an existing issue for this problem?
- [X] I have searched the existing issues
Operating system
Windows
GPU vendor
Nvidia (CUDA)
GPU model
RTX 3090
GPU VRAM
24gb
Version number
4.2.4
Browser
Firefox 127
Python dependencies
No response
What happened
Invoke installs this model as a VAE instead of an sdxl lightning checkpoint.
What you expected to happen
Expected to install as any other sdxl checkpoint
How to reproduce the problem
Install the model
Additional context
This was reproduced by another member in the discord and so far has only seemed to be an issue with this particular model.
Discord username
No response
I'll get to this in another couple of days -- have other issues to deal with first!
Same also happens with this. In 4.0.4 it was even worse because somehow it was identified as a sd-1 vae