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

Name "dataset' no defined

Bobo-Shaba opened this issue · comments

I'm trying to train SD with my own images but I keep getting this error in training section
NameError Traceback (most recent call last)
/tmp/ipykernel_127/4096925038.py in
19 token = "BoboPerson"
20
---> 21 reg_data_root = "/workspace/Dreambooth-Stable-Diffusion/outputs/" + dataset
22
23 get_ipython().system('rm -rf training_images/.ipynb_checkpoints')

NameError: name 'dataset' is not defined

you didn't run one of the regularization image cells that sets a variable named dataset which is used in the training cell as part of a folder path. if you are providing your own reg. images then make sure that is set to whatever your folder name is

Thanks, I didn't realize i skipped a step but new errors keep popping up.

Traceback (most recent call last):
File "main.py", line 2, in
from ldm.modules.pruningckptio.py import PruningCheckpointIO
ModuleNotFoundError: No module named 'ldm.modules.pruningckptio'

when I went through the Idm file 'ldm.modules.pruningckptio.py' does exist.

If I remove line 2 from main.py I get a different error (had no reason to remove it just annoyed)

Traceback (most recent call last):
File "main.py", line 8, in
import pytorch_lightning as pl
ModuleNotFoundError: No module named 'pytorch_lightning'

from ldm.modules.pruningckptio.py import PruningCheckpointIO

Then that means your ENV wasn't built properly or didn't finish. pruningckptio.py is needed each time a checkpoint is created. You're just going to make things worse by removing references to it thinking it will fix it.

start again and make sure the BUILD ENV cell completes