New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Full Dreambooth IF stage II upscaling #3561
Full Dreambooth IF stage II upscaling #3561
Conversation
if text_encoder is not None: | ||
pipeline_args["text_encoder"] = accelerator.unwrap_model(text_encoder) | ||
|
||
if vae is not None: | ||
pipeline_args["vae"] = vae | ||
|
||
if text_encoder is not None: | ||
text_encoder = accelerator.unwrap_model(text_encoder) | ||
|
||
# create pipeline (note: unet and vae are loaded again in float32) | ||
pipeline = DiffusionPipeline.from_pretrained( | ||
args.pretrained_model_name_or_path, | ||
tokenizer=tokenizer, | ||
text_encoder=text_encoder, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This was a bug I introduced, we should still always pass text_encoder to the validation pipeline even if it's None since that indicates we pre-computed text embeddings
The documentation is not available anymore as the PR was closed or merged. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks good to me, but having some tests for the LoRA mixin would be nice here
* update dreambooth lora to work with IF stage II * Update dreambooth script for IF stage II upscaler
rebased on top of #3560