update flax controlnet training script #2951
Merged
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
|
The documentation is not available anymore as the PR was closed or merged. |
sayakpaul
reviewed
Apr 3, 2023
Comment on lines
+53
to
+54
| LARGE_ENOUGH_NUMBER = 100 | ||
| PngImagePlugin.MAX_TEXT_CHUNK = LARGE_ENOUGH_NUMBER * (1024**2) |
There was a problem hiding this comment.
Maybe add a comment for the users to know why this needs to be set?
There was a problem hiding this comment.
What exactly does this change do here?
There was a problem hiding this comment.
added a comment there - to prevent an error I would get when working with coyo700m "Decompressed Data Too Large"
sayakpaul
reviewed
Apr 3, 2023
Comment on lines
362
to
366
| parser.add_argument( | ||
| "--load_from_disk", | ||
| action="store_true", | ||
| help="If True, will load a dataset that was previously saved using [`save_to_disk`] from `--train_data_dir`", | ||
| ) |
There was a problem hiding this comment.
Provide a link to the load_from_disk documentation?
There was a problem hiding this comment.
Also, the help seems a bit unclear to me. How does the dataset need to be saved?
nit: I think we can just do save_to_disk instead of [save_to_disk].
sayakpaul
reviewed
Apr 3, 2023
Comment on lines
+1025
to
+1028
| controlnet.save_pretrained( | ||
| f"{args.output_dir}/{global_step}", | ||
| params=get_params_to_save(state.params), | ||
| ) |
sayakpaul
approved these changes
Apr 3, 2023
w4ffl35
pushed a commit
to w4ffl35/diffusers
that referenced
this pull request
Apr 14, 2023
* load_from_disk + checkpointing_steps * apply feedback
dg845
pushed a commit
to dg845/diffusers
that referenced
this pull request
May 6, 2023
* load_from_disk + checkpointing_steps * apply feedback
AmericanPresidentJimmyCarter
pushed a commit
to AmericanPresidentJimmyCarter/diffusers
that referenced
this pull request
Apr 26, 2024
* load_from_disk + checkpointing_steps * apply feedback
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 makes a few modifications to the flax controlnet training script in order to run with larger dataset:
load_from_diskValueError: Decompressed Data Too Largeerror that I got from torch dataloaderCenterCropto image transformation so that batching will work for images with different sizes and different width/ height