JoePenna / Dreambooth-Stable-Diffusion

Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) by way of Textual Inversion (https://arxiv.org/abs/2208.01618) for Stable Diffusion (https://arxiv.org/abs/2112.10752). Tweaks focused on training faces, objects, and styles.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Upload Images in Dreambooth Training Environment Setup fails on dreambooth_joepenna.ipynb

devonuto opened this issue · comments

Uploading training images...

AttributeError Traceback (most recent call last)
/workspace/Dreambooth-Stable-Diffusion/JupyterNotebookHelpers/setup_training.py in submit_form_click(self, b)
194 return
195 else:
--> 196 self.handle_training_images(uploaded_training_images)
197
198 # Regularization Images

/workspace/Dreambooth-Stable-Diffusion/JupyterNotebookHelpers/setup_training.py in handle_training_images(self, uploaded_images)
263 image_widgets = []
264 for i, img in enumerate(uploaded_images):
--> 265 images.append(img.name)
266 image_widgets.append(widgets.Image(
267 value=img.content,

AttributeError: 'str' object has no attribute 'name'

Just using the training images upload button and selecting a bunch of images and hitting the Save button.

Are you using Runpod? I've seen this error if you use the runpod/pytorch-latest docker image template. Try using the runpod/pytorch-3.10-1.13.1-116 image instead.

More about this here:
#170 (comment)

I was using runpod/pytorch:3.10-2.0.0-117

@yushan777 thanks, that seems to have solved it.