This repository was archived by the owner on Feb 7, 2025. It is now read-only.
445 fix controlnet tutorial #448
Merged
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
added 2 commits
December 13, 2023 16:23
…olNetDiffusionInferer to clean up the code. Ran the notebook.
Closed
ericspod
reviewed
Dec 15, 2023
Comment on lines
+408
to
+424
| # Without using an inferer: | ||
| # progress_bar_sampling = tqdm(scheduler.timesteps, total=len(scheduler.timesteps), ncols=110) | ||
| # progress_bar_sampling.set_description("sampling...") | ||
| # sample = torch.randn((1, 1, 64, 64)).to(device) | ||
| # for t in progress_bar_sampling: | ||
| # with torch.no_grad(): | ||
| # with autocast(enabled=True): | ||
| # down_block_res_samples, mid_block_res_sample = controlnet( | ||
| # x=sample, timesteps=torch.Tensor((t,)).to(device).long(), controlnet_cond=masks[0, None, ...] | ||
| # ) | ||
| # noise_pred = model( | ||
| # sample, | ||
| # timesteps=torch.Tensor((t,)).to(device), | ||
| # down_block_additional_residuals=down_block_res_samples, | ||
| # mid_block_additional_residual=mid_block_res_sample, | ||
| # ) | ||
| # sample, _ = scheduler.step(model_output=noise_pred, timestep=t, sample=sample) |
There was a problem hiding this comment.
Do we want to leave this here or just point people to the definition of the inferer's sample method?
There was a problem hiding this comment.
I was just leaving them there in case a user did not want to use the inferer, as it was previously like that
There was a problem hiding this comment.
I think its OK to leave it there, it might help users get a bit more insight into what the inferer is actually doing under the hood
marksgraham
approved these changes
Dec 15, 2023
# for free
to subscribe to this conversation on GitHub.
Already have an account?
#.
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.
I fixed some typos in the Controlnet tutorial, and included new ControlNetDiffusionInferer functionality to make the code cleaner. The notebook's been ran again to account for modifications.
In response to: #443