Finetune script using the diffusers and datasets library #137
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
frutiemax92
force-pushed
the
train_pixart_diffusers
branch
2 times, most recently
from
3d7d91e
to
29b8730
Compare
frutiemax92
force-pushed
the
train_pixart_diffusers
branch
from
29b8730
to
c6e914e
Compare
|
Tested it with 2 GPUs on a docker container on runpod, it is working after some troublesome docker configuration issues. |
frutiemax92
force-pushed
the
train_pixart_diffusers
branch
2 times, most recently
from
16c1a4c
to
bcf2194
Compare
frutiemax92
force-pushed
the
train_pixart_diffusers
branch
from
bcf2194
to
d0cf2a3
Compare
|
The code is working good now this should be useful for some people. |
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Outdated suggestions cannot be applied.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 script combines the T5 embeddings and VAE features extraction and finetuning. It also supports the usual folder with images and captions inside and also the huggingface dataset with the possibility of adding the embeddings and features and push the dataset to the hub. It uses also Accelerate and the mapping of the dataset uses multiprocessing with multi-gpu capabilities. It features the basic constant learning parameters but this is easily adjustable.