Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-20 01:31:13 +02:00
Code Issues Packages Projects Releases Wiki Activity

cleanup

Browse Source 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
This commit is contained in:
Vladimir Mandic
2024-10-03 10:27:18 -04:00
parent 3b4120db48
commit 2a99654dd2
2 changed files with 2 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+2 -2
View File
@@ -11,7 +11,7 @@
- Full rewrite of **sampler options**, not far more streamlined with tons of new options to tweak scheduler behavior
- Improved **LoRA** detection and handling for all supported models
And other goodies like multiple XYZ grid improvements, additional Flux controlnets, additional interrogate models, better LoRA tags support, and more...
And other goodies like multiple *XYZ grid* improvements, additional *Flux ControlNets*, additional *Interrogate models*, better *LoRA tags* support, and more...
### Details for 2024-10-03
@@ -45,7 +45,7 @@ And other goodies like multiple XYZ grid improvements, additional Flux controlne
- quite a few well-known schedulers are just variations of settings, for example:
- euler sgm is euler with trailing spacing and sample prediction type
- dpm 2m or 3m are dpm 1s with orders of 2 or 3
- dpm 2m sde is dpm++ 2m with sde as solver
- dpm 2m sde is dpm 2m with sde as solver
- xyz grid support for sampler options
- metadata updates for sampler options
- modernui updates for sampler options
modules/sd_vae.py
-2
View File
@@ -278,8 +278,6 @@ def reload_vae_weights(sd_model=None, vae_file=unspecified):
return None
if not shared.native and (shared.cmd_opts.lowvram or shared.cmd_opts.medvram):
lowvram.send_everything_to_cpu()
# else:
# sd_models.move_model(sd_model, devices.cpu)
if not shared.native:
sd_hijack.model_hijack.undo_hijack(sd_model)