Add support for controlnet & sdxl checkpoint conversion #3905
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
lstein
requested review from
GreggHelt2,
StAlKeR7779,
blessedcoolant,
brandonrising and
damian0815
as code owners
1 task
blessedcoolant
requested review from
maryhipp and
psychedelicious
as code owners
blessedcoolant
approved these changes
Jul 26, 2023
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Outdated suggestions cannot be applied.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.
What type of PR is this? (check all applicable)
Have you discussed this change with the InvokeAI team?
Have you updated all relevant documentation?
Description
This PR adds support for loading and converting checkpoint-format ControlNet and SDXL models. The SDXL and SDXL-refiner model conversions are working; however saving the unet in safetensors format leads to corrupted model files, so currently is saving in .bin format (after scanning the input model).
ControlNet conversion seems to be working but needs further testing.
To use this PR, you will need to copy the files
invokeai/configs/stable-diffusion/sd_xl_base.yamlandinvokeai/configs/stable-diffusion/sd_xl_refiner.yamlintoINVOKEAI/configs/stable-diffusion. You will also need to runinvokeai-configure --yes --skip-sdin order to install additional core model files needed by the converter.