Deduplicate sampling/demo code #76
Open
Conversation
This file contains 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
Merged
akx
force-pushed
the
dedupe
branch
2 times, most recently
from
6020210
to
5aef27f
Compare
…el mover context, and deduplicate
|
I didn't see this before starting on #102 or it would have saved me some work :( Regardless, I think I addressed the same things here, but let me know if you spot anything missing or have feedback on it. I believe my model swapping method ends up more flexible? |
|
Sorry you ended up doing duplicate work. I should have maybe pinged you harder here... (Maybe it'd be worth it to review the rest of my open PRs to avoid more of the same..?) I'm currently on vacation so it's a bit hard to review and compare the PRs, sorry 🏖️ |
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Outdated suggestions cannot be applied.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.
This PR deduplicates the code inadvertently readded in #69 to use the refactored helpers implemented in #57.
Most of the commits are simple mechanical refactorings, aside from:
sgm.util.load_model_from_confighad to be changed not tomodel.eval()(which was already done in Minimal txt2img example #60)do_sampleanddo_txt2imgfrom the sampling demo with the refactored helpers, and adds a newmove_modelcontext manager argument to implement low-VRAM mode. (I think it turned out pretty elegant.)👉 Since I do not have a beefy enough CUDA device at my easy disposal, I didn't test the streamlit demo yet.