Make T2I Adapters work with any resolution supported by the models #7215
Conversation
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
github-actions
bot
added
python
|
The UI checks are here: https://github.com/dunkeroni/InvokeAI/blob/t2i_resolution_hack/invokeai/frontend/web/src/common/hooks/useIsReadyToEnqueue.ts#L205-L243 Those don't look right to me - I think those |
|
UI checks have been removed and T2I can now be used at arbitrary resolutions and scaling in the Canvas editor. |
dunkeroni
requested review from
psychedelicious,
blessedcoolant,
maryhipp,
hipsterusername,
lstein,
brandonrising and
RyanJDick
as code owners
psychedelicious
approved these changes
Oct 31, 2024
hipsterusername
approved these changes
Nov 1, 2024
auto-merge was automatically disabled
November 1, 2024 02:19
Rebase failed
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Summary
This change mimics the unet padding strategy to align T2I featuremaps with the latents during denoising. It also slightly adjusts the crop and scale logic so that the control will match the input image without shifting when it needs to pad.
Related Issues / Discussions
QA Instructions
Image generated at 1032x1024
Image generated at 1080x1040 to prove feature alignment.
Edge artifacts on the bottom and right are a result of SDXL's unet padding, and t2i influence will be cut off in those regions.
Merge Plan
Contingent on #7205
Currently the Canvas UI prevents users from generating non-64 resolutions while t2i adapter layers are active. Will leave this as a draft until fixing that.
Checklist