cerspense

/

zeroscope_v2_576w

like 467

import torch
from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler
from diffusers.utils import export_to_video
pipe = DiffusionPipeline.from_pretrained("cerspense/zeroscope_v2_576w", torch_dtype=torch.float16)

Occur the following bug:

pipe = DiffusionPipeline.from_pretrained("cerspense/zeroscope_v2_576w", torch_dtype=torch.float16)
File "/opt/conda/lib/python3.9/site-packages/diffusers/pipelines/pipeline_utils.py", line 953, in from_pretrained
loaded_sub_model = load_sub_model(
File "/opt/conda/lib/python3.9/site-packages/diffusers/pipelines/pipeline_utils.py", line 394, in load_sub_model
loaded_sub_model = load_method(os.path.join(cached_folder, name), **loading_kwargs)
File "/opt/conda/lib/python3.9/site-packages/diffusers/models/modeling_utils.py", line 426, in from_pretrained
allow_pickle = True
ValueError: Cannot load <class 'diffusers.models.autoencoder_kl.AutoencoderKL'> from cerspense/zeroscope_v2_576w/vae because the following keys are missing:
encoder.mid_block.attentions.0.proj_attn.weight, decoder.mid_block.attentions.0.value.bias, decoder.mid_block.attentions.0.key.bias, decoder.mid_block.attentions.0.query.bias, encoder.mid_block.attentions.0.value.weight, encoder.mid_block.attentions.0.query.weight, decoder.mid_block.attentions.0.proj_attn.bias, decoder.mid_block.attentions.0.proj_attn.weight, decoder.mid_block.attentions.0.query.weight, decoder.mid_block.attentions.0.key.weight, encoder.mid_block.attentions.0.key.bias, encoder.mid_block.attentions.0.value.bias, encoder.mid_block.attentions.0.key.weight, decoder.mid_block.attentions.0.value.weight, encoder.mid_block.attentions.0.proj_attn.bias, encoder.mid_block.attentions.0.query.bias.
Please make sure to pass low_cpu_mem_usage=False and device_map=None if you want to randomly initialize those weights or else make sure your checkpoint file is correct.