Skip to content

always unload re-used but modified models - Fixed bad outputs in some Upscaler / Lora flows #10724

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
comfyanonymous merged 1 commit into from
Nov 12, 2025
Merged

always unload re-used but modified models - Fixed bad outputs in some Upscaler / Lora flows #10724

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 1 addition & 4 deletions comfy/model_management.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -503,10 +503,7 @@ def model_load(self, lowvram_model_memory=0, force_patch_weights=False):
use_more_vram = lowvram_model_memory
if use_more_vram == 0:
use_more_vram = 1e32
if use_more_vram > 0:
self.model_use_more_vram(use_more_vram, force_patch_weights=force_patch_weights)
else:
self.model.partially_unload(self.model.offload_device, -use_more_vram, force_patch_weights=force_patch_weights)
self.model_use_more_vram(use_more_vram, force_patch_weights=force_patch_weights)

real_model = self.model.model

Expand Down
3 changes: 3 additions & 0 deletions comfy/model_patcher.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -928,6 +928,9 @@ def partially_load(self, device_to, extra_memory=0, force_patch_weights=False):
extra_memory += (used - self.model.model_loaded_weight_memory)

self.patch_model(load_weights=False)
if extra_memory < 0 and not unpatch_weights:
self.partially_unload(self.offload_device, -extra_memory, force_patch_weights=force_patch_weights)
return 0
full_load = False
if self.model.model_lowvram == False and self.model.model_loaded_weight_memory > 0:
self.apply_hooks(self.forced_hooks, force_apply=True)
Expand Down