MPDynamic: force load flux img_in weight (Fixes flux1 canny+depth lora crash)#12446
Merged
comfyanonymous merged 2 commits intoComfy-Org:masterfrom Feb 16, 2026
Merged
Conversation
rattus128
requested review from
Kosinkadink,
comfyanonymous and
guill
as code owners
nick-morhun
reviewed
Feb 14, 2026
| self.partially_unload_ram(1e32) | ||
| self.partially_unload(None, 1e32) | ||
|
|
||
| keys = list(self.backup.keys()) |
Contributor
Author
There was a problem hiding this comment.
I think it came with the copy paste TBH
This lets the loader know if a lora will change the shape of a weight so it can take appropriate action.
This weight is a bit special, in that the lora changes its geometry. This is rather unique, not handled by existing estimate and doesn't work for either offloading or dynamic_vram. Fix for dynamic_vram as a special case. Ideally we can fully precalculate these lora geometry changes at load time, but just get these models working first.
rattus128
force-pushed
the
prs/dynamic-vram-fixes/flux-img-in
branch
from
0c75f1b to
017d0b4
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This weight is a bit special, in that the lora changes its geometry. This situation is very unique: its not handled by existing estimates and doesn't work for either offloading or dynamic_vram.
Fix for dynamic_vram as a special case. Ideally we can fully precalculate these lora geometry changes at load time, but just get these models working first.
Example Test Conditions:
RTX5090, linux, --fast dynamic_vram, Flux1 + flux1-depth-dev-lora
Before:
After: