Spaces:

levihsu

/

OOTDiffusion

like 784

Running on Zero

I did a recent pull, installed everything on Ubuntu... just to play around with this library and I get the following traceback. Any suggestions? Thank you for this, I'd love to set this up and play around with it.

Traceback (most recent call last):
File "/home/ubuntu/code/OOTDiffusion/run/run_ootd.py", line 11, in
from ootd.inference_ootd_hd import OOTDiffusionHD
File "/home/ubuntu/code/OOTDiffusion/ootd/inference_ootd_hd.py", line 16, in
from pipelines_ootd.pipeline_ootd import OotdPipeline
File "/home/ubuntu/code/OOTDiffusion/ootd/pipelines_ootd/pipeline_ootd.py", line 27, in
from .unet_vton_2d_condition import UNetVton2DConditionModel
File "/home/ubuntu/code/OOTDiffusion/ootd/pipelines_ootd/unet_vton_2d_condition.py", line 23, in
from .unet_vton_2d_blocks import (
File "/home/ubuntu/code/OOTDiffusion/ootd/pipelines_ootd/unet_vton_2d_blocks.py", line 23, in
from .transformer_vton_2d import Transformer2DModel
File "/home/ubuntu/code/OOTDiffusion/ootd/pipelines_ootd/transformer_vton_2d.py", line 29, in
from diffusers.models.embeddings import CaptionProjection, PatchEmbed
ImportError: cannot import name 'CaptionProjection' from 'diffusers.models.embeddings' (/opt/conda/envs/ootd/lib/python3.10/site-packages/diffusers/models/embeddings.py)