[Bug]: sd_model.model.diffusion_model.dtype for SDXL still reports float when using --precison half #16221
Open
4 of 6 tasks
Labels
bug-report
Report of a bug, yet to be confirmed
Checklist
What happened?
sd_models_xl.extend_sdxl()
adds ashared.sd_model.model.diffusion_model.dtype
attribute to SDXL models, which is not updated after casting to float16 when using--precision half
.Anything relying on this attribute to determine the dtype of SDXL models will see float instead of float16.
SD1.5 models are unaffected from what I've seen.
I know of at least one extension that checks this attribute to determine the unet's dtype and is broken due to the misreported dtype: aria1th/sd-webui-deepcache-standalone#9
Hardcoding the extension to use float16 or using
devices.dtype_unet
effectively works around the bug.Steps to reproduce the problem
--precision half
Refreshes caches when step is divisible by number
> 1float
based on misreported dtype but receivingfloat16
insteadWhat should have happened?
Extension runs without crashing.
What browsers do you use to access the UI ?
Mozilla Firefox
Sysinfo
sysinfo-2024-07-18-14-49.json
Console logs
Additional information
No response
The text was updated successfully, but these errors were encountered: