models_server.py raising a value error. Many missing keys...

Open machina20 opened this issue 2 years ago • 4 comments

Fetching 27 files: 100%|█████████████████████████████████████████████████████████████████████████| 27/27 [00:00<00:00, 3392.03it/s]
`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["id2label"]` will be overriden.
Traceback (most recent call last):
  File "models_server.py", line 342, in <module>
    pipes = load_pipes(local_deployment)
  File "models_server.py", line 137, in load_pipes
    "model": DiffusionPipeline.from_pretrained(f"{local_fold}/runwayml/stable-diffusion-v1-5"),
  File "/home/machi/anaconda3/envs/jarvis/lib/python3.8/site-packages/diffusers/pipelines/pipeline_utils.py", line 948, in from_pretrained
    loaded_sub_model = load_sub_model(
  File "/home/machi/anaconda3/envs/jarvis/lib/python3.8/site-packages/diffusers/pipelines/pipeline_utils.py", line 393, in load_sub_model
    loaded_sub_model = load_method(os.path.join(cached_folder, name), **loading_kwargs)
  File "/home/machi/anaconda3/envs/jarvis/lib/python3.8/site-packages/diffusers/models/modeling_utils.py", line 561, in from_pretrained
    raise ValueError(
ValueError: Cannot load <class 'diffusers.models.unet_2d_condition.UNet2DConditionModel'> from models/runwayml/stable-diffusion-v1-5/unet because the following keys are missing: 
 up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_v.weight, down_blocks.2.resnets.1.norm2.bias, up_blocks.1.resnets.0.conv1.bias, up_blocks.1.attentions.2.norm.bias, down_blocks.2.resnets.1.norm1.weight, down_blocks.0.resnets.1.norm1.weight, down_blocks.2.attentions.0.transformer_blocks.0.norm2.weight, up_blocks.1.resnets.2.conv_shortcut.weight, up_blocks.1.resnets.2.conv2.bias, down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_out.0.bias, up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_out.0.bias, down_blocks.0.attentions.0.transformer_blocks.0.norm2.bias, up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_v.weight, down_blocks.2.attentions.1.proj_out.bias, up_blocks.0.resnets.0.time_emb_proj.bias, up_blocks.3.attentions.2.transformer_blocks.0.ff.net.2.weight, down_blocks.0.attentions.0.transformer_blocks.0.ff.net.2.bias, up_blocks.2.resnets.1.norm2.weight, up_blocks.2.resnets.2.norm2.weight, up_blocks.3.attentions.2.norm.weight, down_blocks.3.resnets.0.norm1.bias, down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_q.weight, up_blocks.1.attentions.0.proj_out.bias, up_blocks.2.attentions.2.proj_out.bias, up_blocks.2.resnets.0.conv2.weight, up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_out.0.weight, up_blocks.1.attentions.0.transformer_blocks.0.norm3.bias, down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_out.0.weight, down_blocks.1.attentions.0.transformer_blocks.0.ff.net.0.proj.weight, up_blocks.1.resnets.1.conv2.bias, down_blocks.2.attentions.0.transformer_blocks.0.ff.net.2.bias, down_blocks.2.resnets.1.conv2.weight, mid_block.attentions.0.transformer_blocks.0.attn2.to_out.0.weight, down_blocks.2.resnets.0.norm1.bias, down_blocks.2.attentions.0.proj_in.weight, down_blocks.0.attentions.1.transformer_blocks.0.norm1.weight, up_blocks.3.attentions.0.transformer_blocks.0.ff.net.2.bias, up_blocks.0.resnets.2.conv2.bias, up_blocks.1.attentions.1.transformer_blocks.0.ff.net.2.bias, up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_out.0.weight, up_blocks.2.attentions.1.norm.bias, up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_out.0.bias, down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_out.0.weight, up_blocks.3.attentions.0.transformer_blocks.0.norm1.weight, down_blocks.2.resnets.0.conv1.bias, up_blocks.1.attentions.1.transformer_blocks.0.ff.net.2.weight, up_blocks.2.attentions.0.transformer_blocks.0.norm1.bias, down_blocks.2.resnets.0.conv2.bias, down_blocks.1.resnets.0.norm2.bias, up_blocks.3.attentions.1.transformer_blocks.0.ff.net.0.proj.weight, mid_block.resnets.0.conv1.bias, up_blocks.3.attentions.2.transformer_blocks.0.ff.net.2.bias, up_blocks.1.attentions.1.transformer_blocks.0.norm1.bias, up_blocks.0.upsamplers.0.conv.bias, down_blocks.2.attentions.1.proj_in.weight, up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_k.weight, up_blocks.2.attentions.0.proj_in.bias, down_blocks.0.attentions.0.transformer_blocks.0.norm2.weight, down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_out.0.weight, up_blocks.0.resnets.2.conv1.weight, down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_k.weight, up_blocks.1.resnets.0.norm2.weight, up_blocks.2.resnets.1.time_emb_proj.weight, down_blocks.1.attentions.0.norm.bias, up_blocks.3.resnets.0.norm2.bias, up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_k.weight, down_blocks.1.resnets.1.norm2.weight, up_blocks.2.resnets.0.conv_shortcut.bias, up_blocks.3.attentions.0.transformer_blocks.0.norm1.bias, down_blocks.2.attentions.1.transformer_blocks.0.ff.net.0.proj.weight, up_blocks.0.resnets.2.conv1.bias, up_blocks.3.attentions.1.norm.weight, mid_block.attentions.0.transformer_blocks.0.attn1.to_out.0.bias, up_blocks.2.attentions.2.transformer_blocks.0.ff.net.0.proj.bias, down_blocks.1.attentions.1.transformer_blocks.0.norm1.bias, up_blocks.1.attentions.0.proj_in.bias, up_blocks.1.resnets.2.norm1.weight, up_blocks.1.resnets.1.norm2.weight, up_blocks.0.resnets.1.conv2.bias, up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_k.weight, down_blocks.2.resnets.0.conv_shortcut.bias, down_blocks.2.attentions.1.norm.weight, down_blocks.0.attentions.1.norm.weight, down_blocks.1.attentions.0.transformer_blocks.0.ff.net.0.proj.bias, up_blocks.3.resnets.1.norm2.weight, up_blocks.0.resnets.0.time_emb_proj.weight, down_blocks.1.resnets.1.time_emb_proj.weight, up_blocks.2.attentions.0.transformer_blocks.0.norm1.weight, down_blocks.1.attentions.0.transformer_blocks.0.norm2.bias, down_blocks.0.attentions.1.proj_out.weight, up_blocks.0.resnets.1.conv_shortcut.weight, up_blocks.3.resnets.0.conv1.weight, mid_block.attentions.0.norm.weight, up_blocks.3.resnets.2.conv2.bias, down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_k.weight, up_blocks.3.resnets.2.time_emb_proj.bias, up_blocks.3.resnets.2.norm1.weight, mid_block.attentions.0.transformer_blocks.0.norm1.bias, mid_block.attentions.0.proj_out.weight, down_blocks.0.attentions.0.proj_in.weight, up_blocks.0.resnets.2.norm2.weight, up_blocks.3.attentions.1.transformer_blocks.0.norm2.bias, up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_out.0.weight, up_blocks.3.attentions.2.transformer_blocks.0.ff.net.0.proj.weight, up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_q.weight, up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_out.0.weight, down_blocks.1.attentions.1.transformer_blocks.0.ff.net.0.proj.bias, down_blocks.3.resnets.0.norm2.weight, up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_out.0.bias, up_blocks.0.resnets.0.conv1.bias, down_blocks.0.attentions.0.proj_in.bias, down_blocks.2.attentions.1.proj_in.bias, up_blocks.2.attentions.2.proj_in.weight, up_blocks.3.resnets.1.conv_shortcut.weight, down_blocks.1.attentions.1.transformer_blocks.0.ff.net.2.bias, up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_v.weight, up_blocks.1.attentions.0.norm.bias, up_blocks.2.resnets.0.conv2.bias, down_blocks.2.attentions.0.transformer_blocks.0.ff.net.2.weight, up_blocks.1.resnets.2.time_emb_proj.weight, down_blocks.2.resnets.0.norm2.bias, up_blocks.1.resnets.0.time_emb_proj.bias, up_blocks.3.resnets.1.norm1.weight, up_blocks.2.attentions.1.transformer_blocks.0.ff.net.0.proj.bias, up_blocks.0.resnets.1.conv_shortcut.bias, up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_k.weight, up_blocks.1.attentions.2.transformer_blocks.0.norm2.bias, down_blocks.3.resnets.1.norm1.weight, up_blocks.2.resnets.1.conv1.weight, down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_out.0.bias, down_blocks.0.resnets.0.norm2.bias, mid_block.attentions.0.transformer_blocks.0.attn2.to_q.weight, down_blocks.3.resnets.1.norm2.weight, up_blocks.0.resnets.0.conv_shortcut.weight, up_blocks.1.attentions.0.transformer_blocks.0.norm1.bias, down_blocks.2.attentions.0.transformer_blocks.0.norm1.bias, up_blocks.0.resnets.0.conv2.bias, up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_out.0.bias, conv_out.bias, up_blocks.1.attentions.2.proj_out.weight, up_blocks.3.attentions.1.proj_in.weight, up_blocks.3.attentions.1.proj_out.weight, down_blocks.0.resnets.1.norm2.weight, up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_q.weight, down_blocks.0.attentions.1.transformer_blocks.0.norm3.weight, up_blocks.1.resnets.0.norm2.bias, down_blocks.0.resnets.1.conv1.bias, up_blocks.3.resnets.1.conv1.weight, mid_block.attentions.0.transformer_blocks.0.ff.net.0.proj.bias, up_blocks.2.attentions.0.transformer_blocks.0.ff.net.2.weight, down_blocks.2.attentions.1.transformer_blocks.0.norm3.weight, up_blocks.2.attentions.0.transformer_blocks.0.norm2.bias, down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_out.0.bias, down_blocks.2.resnets.1.time_emb_proj.weight, down_blocks.0.attentions.0.transformer_blocks.0.norm3.weight, up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_k.weight, down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_k.weight, mid_block.attentions.0.transformer_blocks.0.norm2.bias, down_blocks.1.resnets.1.norm2.bias, up_blocks.3.attentions.1.transformer_blocks.0.norm2.weight, up_blocks.3.attentions.2.transformer_blocks.0.norm2.bias, up_blocks.2.resnets.1.norm1.weight, down_blocks.1.attentions.1.transformer_blocks.0.ff.net.0.proj.weight, up_blocks.2.attentions.1.transformer_blocks.0.norm1.weight, up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_out.0.weight, up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_k.weight, up_blocks.3.resnets.2.norm1.bias, down_blocks.0.attentions.1.proj_in.bias, up_blocks.1.attentions.2.proj_in.bias, up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_v.weight, up_blocks.3.attentions.2.transformer_blocks.0.norm3.bias, up_blocks.0.resnets.0.norm2.bias, down_blocks.1.resnets.0.conv_shortcut.weight, up_blocks.3.resnets.1.time_emb_proj.bias, up_blocks.3.resnets.1.conv2.weight, up_blocks.3.attentions.0.proj_out.weight, down_blocks.1.resnets.0.conv1.weight, up_blocks.1.attentions.2.norm.weight, up_blocks.1.attentions.0.transformer_blocks.0.norm2.bias, down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_v.weight, time_embedding.linear_2.bias, down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_out.0.weight, up_blocks.1.attentions.1.transformer_blocks.0.norm3.bias, up_blocks.2.attentions.0.transformer_blocks.0.ff.net.0.proj.bias, down_blocks.2.attentions.1.transformer_blocks.0.ff.net.0.proj.bias, down_blocks.1.attentions.0.proj_in.bias, up_blocks.2.resnets.1.conv2.bias, down_blocks.0.attentions.1.norm.bias, down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_q.weight, down_blocks.2.resnets.0.conv1.weight, up_blocks.1.attentions.2.transformer_blocks.0.ff.net.0.proj.weight, up_blocks.2.attentions.1.transformer_blocks.0.ff.net.2.weight, mid_block.attentions.0.transformer_blocks.0.attn2.to_v.weight, up_blocks.3.attentions.2.transformer_blocks.0.norm2.weight, up_blocks.2.resnets.2.norm2.bias, down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_v.weight, down_blocks.0.resnets.1.time_emb_proj.bias, up_blocks.0.resnets.2.conv_shortcut.bias, down_blocks.2.attentions.1.transformer_blocks.0.norm1.weight, down_blocks.0.attentions.0.transformer_blocks.0.norm3.bias, up_blocks.3.attentions.2.proj_out.bias, down_blocks.3.resnets.0.time_emb_proj.weight, down_blocks.2.attentions.0.transformer_blocks.0.norm3.bias, down_blocks.0.attentions.1.transformer_blocks.0.ff.net.0.proj.bias, down_blocks.1.attentions.1.transformer_blocks.0.norm2.bias, up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_q.weight, up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_out.0.bias, up_blocks.1.resnets.1.norm2.bias, down_blocks.1.attentions.1.transformer_blocks.0.norm2.weight, up_blocks.0.resnets.2.norm1.weight, up_blocks.0.resnets.2.conv_shortcut.weight, up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_q.weight, up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_q.weight, up_blocks.2.resnets.0.conv1.weight, up_blocks.3.attentions.0.transformer_blocks.0.norm2.weight, down_blocks.0.attentions.0.norm.weight, up_blocks.2.attentions.0.proj_out.weight, down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_k.weight, down_blocks.2.resnets.0.time_emb_proj.weight, up_blocks.2.resnets.2.time_emb_proj.bias, up_blocks.3.resnets.0.time_emb_proj.weight, down_blocks.0.downsamplers.0.conv.weight, down_blocks.0.resnets.1.conv2.weight, up_blocks.3.resnets.0.conv_shortcut.bias, mid_block.attentions.0.transformer_blocks.0.attn1.to_k.weight, down_blocks.0.attentions.1.transformer_blocks.0.ff.net.2.bias, down_blocks.1.attentions.1.norm.bias, down_blocks.1.resnets.0.norm1.weight, up_blocks.2.attentions.2.transformer_blocks.0.norm2.bias, up_blocks.0.resnets.1.norm2.weight, up_blocks.2.upsamplers.0.conv.bias, up_blocks.3.resnets.0.conv1.bias, up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_v.weight, up_blocks.2.attentions.1.proj_in.weight, down_blocks.1.resnets.0.conv2.bias, up_blocks.3.resnets.0.time_emb_proj.bias, up_blocks.2.attentions.2.transformer_blocks.0.norm3.weight, up_blocks.1.resnets.1.conv1.bias, up_blocks.2.attentions.2.transformer_blocks.0.norm3.bias, up_blocks.0.resnets.1.conv2.weight, up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_out.0.bias, up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_out.0.weight, down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_v.weight, down_blocks.0.attentions.0.transformer_blocks.0.norm1.bias, up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_out.0.bias, down_blocks.1.attentions.0.transformer_blocks.0.norm1.weight, down_blocks.0.attentions.1.proj_out.bias, up_blocks.1.attentions.1.proj_out.bias, down_blocks.3.resnets.0.norm1.weight, up_blocks.3.attentions.0.transformer_blocks.0.ff.net.2.weight, mid_block.attentions.0.transformer_blocks.0.ff.net.2.weight, up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_k.weight, up_blocks.2.attentions.1.transformer_blocks.0.norm2.bias, up_blocks.3.attentions.1.norm.bias, down_blocks.1.attentions.0.transformer_blocks.0.norm3.weight, up_blocks.1.resnets.2.conv1.weight, up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_out.0.bias, mid_block.attentions.0.proj_out.bias, down_blocks.1.resnets.0.norm2.weight, up_blocks.0.upsamplers.0.conv.weight, up_blocks.1.resnets.1.time_emb_proj.weight, up_blocks.2.attentions.0.proj_in.weight, up_blocks.2.attentions.2.transformer_blocks.0.norm1.weight, mid_block.resnets.1.time_emb_proj.bias, down_blocks.0.attentions.0.transformer_blocks.0.ff.net.0.proj.weight, down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_k.weight, down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_q.weight, down_blocks.0.resnets.0.norm1.bias, down_blocks.2.resnets.0.norm2.weight, down_blocks.2.attentions.1.transformer_blocks.0.norm3.bias, up_blocks.3.resnets.2.conv_shortcut.bias, up_blocks.1.resnets.1.norm1.bias, time_embedding.linear_2.weight, down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_q.weight, up_blocks.3.resnets.1.conv_shortcut.bias, up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_out.0.bias, up_blocks.1.resnets.0.conv1.weight, down_blocks.3.resnets.1.conv2.weight, down_blocks.0.resnets.0.conv1.bias, mid_block.attentions.0.norm.bias, up_blocks.1.attentions.0.transformer_blocks.0.ff.net.0.proj.weight, up_blocks.2.attentions.2.proj_out.weight, up_blocks.1.attentions.1.proj_in.bias, down_blocks.0.resnets.1.norm2.bias, down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_out.0.weight, up_blocks.1.resnets.0.time_emb_proj.weight, down_blocks.1.resnets.1.norm1.weight, down_blocks.2.attentions.1.transformer_blocks.0.norm2.bias, down_blocks.0.attentions.0.transformer_blocks.0.ff.net.2.weight, up_blocks.1.attentions.1.transformer_blocks.0.norm1.weight, down_blocks.2.attentions.0.proj_in.bias, up_blocks.3.resnets.1.conv1.bias, up_blocks.3.resnets.1.norm1.bias, time_embedding.linear_1.weight, mid_block.attentions.0.transformer_blocks.0.attn1.to_out.0.weight, up_blocks.0.resnets.1.time_emb_proj.weight, up_blocks.3.attentions.1.transformer_blocks.0.norm3.weight, up_blocks.1.resnets.2.norm2.bias, down_blocks.1.attentions.1.transformer_blocks.0.ff.net.2.weight, up_blocks.3.attentions.1.proj_in.bias, up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_q.weight, down_blocks.0.attentions.1.transformer_blocks.0.norm1.bias, down_blocks.0.resnets.0.norm2.weight, down_blocks.1.attentions.1.transformer_blocks.0.norm3.bias, up_blocks.1.attentions.1.transformer_blocks.0.norm3.weight, up_blocks.1.attentions.0.norm.weight, up_blocks.3.attentions.0.norm.bias, down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_out.0.bias, up_blocks.1.resnets.0.conv_shortcut.bias, mid_block.attentions.0.transformer_blocks.0.attn2.to_out.0.bias, up_blocks.2.attentions.0.proj_out.bias, down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_k.weight, down_blocks.1.resnets.1.conv1.weight, up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_k.weight, down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_v.weight, up_blocks.3.attentions.1.transformer_blocks.0.ff.net.0.proj.bias, mid_block.resnets.0.conv2.weight, down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_out.0.bias, down_blocks.1.resnets.1.time_emb_proj.bias, down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_out.0.weight, up_blocks.3.attentions.1.proj_out.bias, down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_out.0.weight, mid_block.resnets.0.norm2.bias, down_blocks.2.attentions.0.transformer_blocks.0.norm3.weight, up_blocks.2.resnets.0.conv1.bias, down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_v.weight, up_blocks.1.attentions.0.proj_in.weight, mid_block.resnets.1.conv1.weight, up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_k.weight, mid_block.attentions.0.proj_in.weight, up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_out.0.bias, up_blocks.0.resnets.1.norm1.weight, up_blocks.3.attentions.2.transformer_blocks.0.norm1.bias, up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_k.weight, down_blocks.2.attentions.1.transformer_blocks.0.ff.net.2.bias, down_blocks.2.downsamplers.0.conv.weight, up_blocks.1.attentions.1.proj_out.weight, conv_in.weight, down_blocks.2.attentions.1.norm.bias, up_blocks.2.attentions.2.transformer_blocks.0.ff.net.2.weight, up_blocks.0.resnets.0.conv2.weight, up_blocks.1.attentions.1.transformer_blocks.0.ff.net.0.proj.weight, down_blocks.1.attentions.1.proj_out.bias, up_blocks.1.attentions.0.transformer_blocks.0.ff.net.2.bias, up_blocks.3.attentions.2.proj_out.weight, up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_v.weight, down_blocks.0.resnets.0.conv1.weight, up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_v.weight, up_blocks.2.attentions.0.transformer_blocks.0.ff.net.0.proj.weight, down_blocks.0.resnets.0.conv2.weight, up_blocks.1.attentions.2.transformer_blocks.0.norm3.weight, down_blocks.0.attentions.0.proj_out.bias, up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_out.0.bias, up_blocks.1.resnets.0.norm1.weight, down_blocks.1.attentions.0.transformer_blocks.0.norm3.bias, up_blocks.2.attentions.2.transformer_blocks.0.ff.net.0.proj.weight, down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_q.weight, up_blocks.2.resnets.2.norm1.bias, down_blocks.1.attentions.0.proj_out.bias, mid_block.resnets.0.time_emb_proj.weight, up_blocks.2.attentions.1.transformer_blocks.0.norm2.weight, mid_block.resnets.0.conv2.bias, down_blocks.3.resnets.1.conv2.bias, down_blocks.2.attentions.0.proj_out.bias, up_blocks.2.attentions.2.norm.weight, down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_out.0.bias, up_blocks.2.resnets.0.norm2.bias, up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_v.weight, up_blocks.2.attentions.1.transformer_blocks.0.ff.net.0.proj.weight, up_blocks.1.resnets.0.conv_shortcut.weight, down_blocks.0.resnets.0.conv2.bias, up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_out.0.bias, up_blocks.3.resnets.0.norm1.weight, up_blocks.3.resnets.1.conv2.bias, down_blocks.1.resnets.1.conv2.bias, up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_out.0.weight, up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_v.weight, down_blocks.1.resnets.1.conv2.weight, up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_q.weight, up_blocks.3.resnets.2.conv1.weight, down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_v.weight, down_blocks.2.attentions.1.transformer_blocks.0.ff.net.2.weight, up_blocks.2.resnets.2.conv1.weight, up_blocks.2.resnets.0.norm1.weight, down_blocks.2.resnets.0.time_emb_proj.bias, down_blocks.2.attentions.1.transformer_blocks.0.norm1.bias, up_blocks.1.resnets.1.conv_shortcut.weight, up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_out.0.weight, up_blocks.1.attentions.0.transformer_blocks.0.ff.net.2.weight, down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_v.weight, up_blocks.1.attentions.1.transformer_blocks.0.ff.net.0.proj.bias, up_blocks.1.attentions.2.transformer_blocks.0.norm1.bias, down_blocks.2.resnets.0.norm1.weight, up_blocks.2.resnets.0.time_emb_proj.weight, up_blocks.3.resnets.0.norm1.bias, mid_block.resnets.0.time_emb_proj.bias, up_blocks.1.resnets.2.norm2.weight, down_blocks.3.resnets.1.norm1.bias, up_blocks.1.resnets.1.conv1.weight, down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_out.0.weight, up_blocks.3.resnets.0.conv2.bias, mid_block.attentions.0.transformer_blocks.0.norm3.weight, up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_out.0.bias, up_blocks.1.resnets.2.conv1.bias, up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_out.0.bias, down_blocks.0.resnets.1.conv1.weight, up_blocks.3.attentions.0.transformer_blocks.0.ff.net.0.proj.bias, down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_k.weight, up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_out.0.bias, up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_v.weight, up_blocks.2.resnets.1.conv1.bias, down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_out.0.bias, up_blocks.1.attentions.1.norm.bias, up_blocks.1.resnets.2.conv2.weight, down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_out.0.weight, down_blocks.0.attentions.1.transformer_blocks.0.ff.net.2.weight, down_blocks.3.resnets.0.time_emb_proj.bias, up_blocks.1.resnets.2.time_emb_proj.bias, up_blocks.1.upsamplers.0.conv.weight, up_blocks.2.resnets.0.norm2.weight, down_blocks.1.attentions.0.norm.weight, up_blocks.2.attentions.0.transformer_blocks.0.norm3.weight, up_blocks.3.attentions.2.transformer_blocks.0.norm1.weight, up_blocks.1.attentions.2.transformer_blocks.0.ff.net.2.bias, mid_block.attentions.0.transformer_blocks.0.ff.net.0.proj.weight, mid_block.resnets.0.norm1.weight, down_blocks.1.resnets.0.time_emb_proj.bias, up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_out.0.weight, down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_v.weight, up_blocks.2.upsamplers.0.conv.weight, conv_norm_out.weight, up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_v.weight, mid_block.resnets.0.conv1.weight, down_blocks.2.resnets.1.time_emb_proj.bias, up_blocks.0.resnets.0.norm1.bias, up_blocks.3.attentions.1.transformer_blocks.0.norm1.bias, down_blocks.1.attentions.1.transformer_blocks.0.norm3.weight, up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_q.weight, down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_k.weight, up_blocks.3.resnets.2.norm2.weight, up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_out.0.weight, up_blocks.3.resnets.1.norm2.bias, up_blocks.1.attentions.2.transformer_blocks.0.norm2.weight, down_blocks.0.attentions.0.transformer_blocks.0.ff.net.0.proj.bias, down_blocks.1.resnets.0.conv1.bias, up_blocks.2.attentions.0.transformer_blocks.0.norm2.weight, up_blocks.2.attentions.1.transformer_blocks.0.norm3.weight, down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_out.0.bias, down_blocks.1.downsamplers.0.conv.bias, down_blocks.0.attentions.1.proj_in.weight, mid_block.resnets.1.conv1.bias, down_blocks.3.resnets.1.time_emb_proj.weight, down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_v.weight, mid_block.attentions.0.transformer_blocks.0.norm1.weight, down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_k.weight, up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_out.0.weight, down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_k.weight, up_blocks.1.attentions.0.transformer_blocks.0.norm2.weight, up_blocks.2.attentions.1.proj_out.bias, up_blocks.2.attentions.2.norm.bias, down_blocks.2.attentions.1.proj_out.weight, up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_q.weight, up_blocks.3.attentions.1.transformer_blocks.0.norm3.bias, up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_q.weight, down_blocks.1.attentions.1.proj_out.weight, conv_in.bias, down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_q.weight, down_blocks.0.downsamplers.0.conv.bias, up_blocks.3.attentions.0.proj_out.bias, down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_v.weight, down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_out.0.weight, up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_q.weight, up_blocks.1.resnets.2.conv_shortcut.bias, down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_v.weight, up_blocks.2.attentions.1.proj_out.weight, conv_norm_out.bias, up_blocks.3.attentions.0.transformer_blocks.0.norm3.weight, up_blocks.3.resnets.0.conv_shortcut.weight, up_blocks.2.resnets.1.time_emb_proj.bias, up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_k.weight, up_blocks.2.resnets.2.conv_shortcut.bias, down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_q.weight, up_blocks.3.attentions.2.proj_in.weight, up_blocks.1.resnets.0.conv2.bias, down_blocks.1.attentions.0.proj_in.weight, down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_out.0.weight, down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_q.weight, up_blocks.1.attentions.0.transformer_blocks.0.norm3.weight, up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_v.weight, down_blocks.2.attentions.1.transformer_blocks.0.norm2.weight, up_blocks.1.attentions.2.proj_out.bias, down_blocks.1.attentions.0.transformer_blocks.0.norm2.weight, up_blocks.3.attentions.0.norm.weight, up_blocks.1.attentions.2.transformer_blocks.0.norm1.weight, up_blocks.3.resnets.2.conv1.bias, down_blocks.1.resnets.0.time_emb_proj.weight, up_blocks.2.resnets.1.conv_shortcut.weight, down_blocks.1.attentions.1.proj_in.weight, mid_block.attentions.0.transformer_blocks.0.attn2.to_k.weight, conv_out.weight, up_blocks.3.attentions.0.proj_in.weight, up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_v.weight, mid_block.resnets.0.norm2.weight, up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_v.weight, up_blocks.3.resnets.0.norm2.weight, down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_q.weight, mid_block.resnets.0.norm1.bias, down_blocks.2.resnets.0.conv_shortcut.weight, up_blocks.3.attentions.1.transformer_blocks.0.ff.net.2.bias, down_blocks.3.resnets.0.conv1.bias, up_blocks.2.resnets.1.conv2.weight, up_blocks.0.resnets.2.conv2.weight, down_blocks.3.resnets.1.conv1.bias, up_blocks.2.resnets.0.norm1.bias, up_blocks.2.resnets.2.norm1.weight, up_blocks.1.attentions.2.transformer_blocks.0.norm3.bias, down_blocks.0.attentions.0.proj_out.weight, up_blocks.2.attentions.1.transformer_blocks.0.ff.net.2.bias, up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_out.0.weight, up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_q.weight, up_blocks.3.resnets.2.norm2.bias, up_blocks.1.resnets.1.conv_shortcut.bias, down_blocks.1.resnets.0.conv_shortcut.bias, up_blocks.3.resnets.2.conv2.weight, up_blocks.2.attentions.1.norm.weight, up_blocks.3.attentions.0.proj_in.bias, mid_block.attentions.0.transformer_blocks.0.norm2.weight, down_blocks.2.resnets.1.conv1.weight, up_blocks.2.attentions.0.transformer_blocks.0.ff.net.2.bias, down_blocks.0.attentions.1.transformer_blocks.0.norm2.bias, down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_out.0.bias, up_blocks.1.attentions.1.transformer_blocks.0.norm2.bias, up_blocks.0.resnets.0.norm2.weight, up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_k.weight, up_blocks.3.attentions.1.transformer_blocks.0.norm1.weight, down_blocks.0.resnets.0.time_emb_proj.weight, mid_block.resnets.1.conv2.bias, time_embedding.linear_1.bias, up_blocks.1.upsamplers.0.conv.bias, up_blocks.1.attentions.2.transformer_blocks.0.ff.net.0.proj.bias, up_blocks.2.resnets.2.conv2.bias, up_blocks.2.attentions.2.transformer_blocks.0.norm2.weight, up_blocks.3.attentions.2.transformer_blocks.0.norm3.weight, mid_block.resnets.1.norm2.bias, mid_block.attentions.0.transformer_blocks.0.norm3.bias, up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_out.0.weight, up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_v.weight, up_blocks.0.resnets.0.norm1.weight, up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_q.weight, down_blocks.2.attentions.0.transformer_blocks.0.norm1.weight, up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_q.weight, up_blocks.1.resnets.0.norm1.bias, mid_block.resnets.1.norm1.weight, down_blocks.1.resnets.0.norm1.bias, up_blocks.3.attentions.1.transformer_blocks.0.ff.net.2.weight, up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_v.weight, up_blocks.2.resnets.0.conv_shortcut.weight, down_blocks.3.resnets.0.conv1.weight, mid_block.attentions.0.transformer_blocks.0.attn1.to_q.weight, down_blocks.2.attentions.0.transformer_blocks.0.ff.net.0.proj.weight, up_blocks.2.resnets.1.norm2.bias, down_blocks.2.resnets.1.norm1.bias, up_blocks.2.resnets.2.conv_shortcut.weight, down_blocks.2.attentions.0.transformer_blocks.0.norm2.bias, down_blocks.2.resnets.1.conv2.bias, up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_k.weight, down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_v.weight, down_blocks.0.resnets.1.conv2.bias, mid_block.attentions.0.transformer_blocks.0.ff.net.2.bias, up_blocks.2.attentions.2.transformer_blocks.0.ff.net.2.bias, up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_q.weight, down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_q.weight, up_blocks.2.attentions.0.transformer_blocks.0.norm3.bias, down_blocks.0.attentions.0.norm.bias, up_blocks.3.resnets.1.time_emb_proj.weight, down_blocks.3.resnets.0.norm2.bias, mid_block.resnets.1.norm2.weight, down_blocks.1.resnets.1.conv1.bias, down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_k.weight, up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_out.0.bias, down_blocks.0.resnets.1.norm1.bias, up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_q.weight, up_blocks.1.resnets.2.norm1.bias, up_blocks.1.resnets.1.conv2.weight, down_blocks.1.attentions.1.transformer_blocks.0.norm1.weight, up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_q.weight, up_blocks.2.attentions.1.transformer_blocks.0.norm3.bias, up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_q.weight, up_blocks.2.attentions.2.proj_in.bias, up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_out.0.weight, up_blocks.0.resnets.1.time_emb_proj.bias, up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_k.weight, up_blocks.3.resnets.0.conv2.weight, up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_v.weight, up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_out.0.bias, up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_k.weight, down_blocks.3.resnets.1.norm2.bias, down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_q.weight, up_blocks.2.resnets.0.time_emb_proj.bias, up_blocks.1.attentions.1.transformer_blocks.0.norm2.weight, mid_block.resnets.1.conv2.weight, up_blocks.2.attentions.0.norm.weight, up_blocks.1.resnets.1.time_emb_proj.bias, up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_k.weight, up_blocks.2.resnets.2.conv2.weight, down_blocks.0.attentions.1.transformer_blocks.0.norm2.weight, up_blocks.0.resnets.2.norm2.bias, up_blocks.0.resnets.1.conv1.bias, up_blocks.1.resnets.1.norm1.weight, down_blocks.3.resnets.0.conv2.weight, up_blocks.2.resnets.1.norm1.bias, down_blocks.1.downsamplers.0.conv.weight, up_blocks.0.resnets.0.conv1.weight, down_blocks.2.attentions.0.norm.weight, up_blocks.1.attentions.0.transformer_blocks.0.norm1.weight, down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_out.0.bias, down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_out.0.bias, up_blocks.2.resnets.1.conv_shortcut.bias, up_blocks.3.resnets.2.time_emb_proj.weight, down_blocks.0.attentions.0.transformer_blocks.0.norm1.weight, up_blocks.2.attentions.0.norm.bias, up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_k.weight, down_blocks.2.attentions.0.norm.bias, up_blocks.1.attentions.0.transformer_blocks.0.ff.net.0.proj.bias, up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_out.0.weight, up_blocks.2.resnets.2.time_emb_proj.weight, down_blocks.0.attentions.1.transformer_blocks.0.norm3.bias, down_blocks.0.attentions.1.transformer_blocks.0.ff.net.0.proj.weight, up_blocks.1.attentions.1.proj_in.weight, down_blocks.2.resnets.1.norm2.weight, mid_block.resnets.1.norm1.bias, down_blocks.2.resnets.1.conv1.bias, up_blocks.0.resnets.1.norm2.bias, down_blocks.2.attentions.0.transformer_blocks.0.ff.net.0.proj.bias, up_blocks.2.resnets.2.conv1.bias, down_blocks.0.resnets.0.time_emb_proj.bias, up_blocks.2.attentions.1.proj_in.bias, down_blocks.1.attentions.0.transformer_blocks.0.ff.net.2.weight, up_blocks.1.resnets.0.conv2.weight, down_blocks.2.downsamplers.0.conv.bias, down_blocks.2.resnets.0.conv2.weight, down_blocks.1.attentions.0.transformer_blocks.0.ff.net.2.bias, up_blocks.1.attentions.2.proj_in.weight, up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_out.0.weight, up_blocks.3.attentions.2.proj_in.bias, down_blocks.3.resnets.0.conv2.bias, up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_v.weight, up_blocks.3.attentions.0.transformer_blocks.0.norm2.bias, up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_out.0.weight, down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_out.0.bias, mid_block.attentions.0.proj_in.bias, up_blocks.3.attentions.2.norm.bias, down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_k.weight, down_blocks.1.resnets.1.norm1.bias, up_blocks.0.resnets.2.time_emb_proj.weight, up_blocks.0.resnets.1.norm1.bias, mid_block.resnets.1.time_emb_proj.weight, down_blocks.1.attentions.1.norm.weight, up_blocks.0.resnets.2.norm1.bias, mid_block.attentions.0.transformer_blocks.0.attn1.to_v.weight, down_blocks.1.attentions.0.transformer_blocks.0.norm1.bias, up_blocks.2.attentions.1.transformer_blocks.0.norm1.bias, up_blocks.0.resnets.0.conv_shortcut.bias, up_blocks.2.attentions.2.transformer_blocks.0.norm1.bias, up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_out.0.bias, up_blocks.3.attentions.2.transformer_blocks.0.ff.net.0.proj.bias, down_blocks.0.resnets.0.norm1.weight, down_blocks.2.attentions.0.proj_out.weight, up_blocks.3.attentions.0.transformer_blocks.0.ff.net.0.proj.weight, up_blocks.1.attentions.1.norm.weight, down_blocks.0.resnets.1.time_emb_proj.weight, up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_out.0.weight, down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_out.0.weight, down_blocks.1.resnets.0.conv2.weight, up_blocks.0.resnets.1.conv1.weight, down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_q.weight, down_blocks.3.resnets.1.time_emb_proj.bias, up_blocks.3.resnets.2.conv_shortcut.weight, up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_k.weight, up_blocks.1.attentions.0.proj_out.weight, down_blocks.1.attentions.0.proj_out.weight, down_blocks.3.resnets.1.conv1.weight, up_blocks.0.resnets.2.time_emb_proj.bias, up_blocks.3.attentions.0.transformer_blocks.0.norm3.bias, up_blocks.1.attentions.2.transformer_blocks.0.ff.net.2.weight, down_blocks.1.attentions.1.proj_in.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.

Apr 11 '23 11:04 machina20

hi, I have the same problem: Cannot load <class 'diffusers.models.unet_2d_condition.UNet2DConditionModel'> from runwayml/stable-diffusion-v1-5 because the following keys are missing…… and how do you deal with it?

Apr 25 '23 14:04 Castrol68

how do you deal with it?

I haven't looked at this repo since I opened the issue, I'll take a look again soon.

May 08 '23 23:05 machina20

I have the same problem ValueError: Cannot load <class 'diffusers.models.unet_2d_condition.UNet2DConditionModel'> from /tmp/tmpp6uv8456/unet because the following keys are missing: up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_out.0.weight, up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_out.0.bias, up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_k.weight, up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_q.weight, up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_out.0.weight, down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_out.0.weight, up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_out.0.bias, up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_v.weight, up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_k.weight, up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_out.0.bias, down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_out.0.weight, up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_out.0.weight, up_blocks.3.attentions.0.transformer_blocks.0.ff.net.0.proj.bias, up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_q.weight, down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_out.0.weight, up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_q.weight, down_blocks.1.attentions.1.transformer_blocks.0.ff.net.0.proj.bias, up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_v.weight, up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_out.0.bias, down_blocks.0.attentions.1.transformer_blocks.0.ff.net.0.proj.bias, up_blocks.1.attentions.1.transformer_blocks.0.ff.net.0.proj.weight, down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_out.0.weight, down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_out.0.weight, up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_q.weight, down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_k.weight, up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_q.weight, up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_k.weight, up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_q.weight, down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_q.weight, up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_k.weight, down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_k.weight, down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_out.0.weight, down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_q.weight, down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_q.weight, down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_v.weight, up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_v.weight, up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_k.weight, up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_k.weight, up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_k.weight, up_blocks.3.attentions.0.transformer_blocks.0.ff.net.0.proj.weight, up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_v.weight, up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_out.0.bias, up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_out.0.bias, up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_out.0.weight, up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_out.0.bias, up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_k.weight, down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_k.weight, up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_v.weight, up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_k.weight, down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_q.weight, mid_block.attentions.0.transformer_blocks.0.attn1.to_q.weight, down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_v.weight, down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_v.weight, mid_block.attentions.0.transformer_blocks.0.ff.net.0.proj.weight, mid_block.attentions.0.transformer_blocks.0.attn1.to_out.0.bias, up_blocks.1.attentions.2.transformer_blocks.0.ff.net.0.proj.weight, down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_out.0.weight, up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_out.0.weight, up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_v.weight, up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_v.weight, up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_q.weight, down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_v.weight, up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_out.0.weight, up_blocks.2.attentions.0.transformer_blocks.0.ff.net.0.proj.weight, down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_out.0.bias, up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_out.0.bias, up_blocks.3.attentions.2.transformer_blocks.0.ff.net.0.proj.weight, up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_out.0.bias, up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_out.0.weight, up_blocks.2.attentions.0.transformer_blocks.0.ff.net.0.proj.bias, up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_k.weight, up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_out.0.bias, down_blocks.1.attentions.0.transformer_blocks.0.ff.net.0.proj.weight, up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_out.0.weight, up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_q.weight, up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_out.0.weight, mid_block.attentions.0.transformer_blocks.0.attn2.to_k.weight, down_blocks.2.attentions.1.transformer_blocks.0.ff.net.0.proj.bias, up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_v.weight, mid_block.attentions.0.transformer_blocks.0.attn1.to_out.0.weight, up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_out.0.weight, down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_v.weight, down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_q.weight, up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_v.weight, up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_out.0.bias, up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_k.weight, up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_q.weight, up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_out.0.weight, down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_q.weight, up_blocks.1.attentions.0.transformer_blocks.0.ff.net.0.proj.bias, down_blocks.2.attentions.1.transformer_blocks.0.ff.net.0.proj.weight, up_blocks.1.attentions.2.transformer_blocks.0.ff.net.0.proj.bias, down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_k.weight, up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_q.weight, up_blocks.2.attentions.1.transformer_blocks.0.ff.net.0.proj.bias, up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_v.weight, up_blocks.2.attentions.2.transformer_blocks.0.ff.net.0.proj.bias, up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_q.weight, up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_out.0.bias, up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_out.0.weight, up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_k.weight, up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_k.weight, down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_out.0.weight, up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_q.weight, down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_v.weight, down_blocks.0.attentions.1.transformer_blocks.0.ff.net.0.proj.weight, up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_out.0.bias, down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_out.0.weight, down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_out.0.bias, down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_out.0.bias, up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_q.weight, up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_q.weight, up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_v.weight, up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_out.0.weight, down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_v.weight, up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_v.weight, mid_block.attentions.0.transformer_blocks.0.attn1.to_k.weight, mid_block.attentions.0.transformer_blocks.0.attn2.to_v.weight, up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_k.weight, up_blocks.3.attentions.1.transformer_blocks.0.ff.net.0.proj.weight, down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_out.0.bias, up_blocks.2.attentions.1.transformer_blocks.0.ff.net.0.proj.weight, down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_out.0.bias, down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_k.weight, up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_v.weight, up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_v.weight, down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_q.weight, down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_q.weight, up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_out.0.bias, up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_k.weight, up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_v.weight, up_blocks.2.attentions.2.transformer_blocks.0.ff.net.0.proj.weight, mid_block.attentions.0.transformer_blocks.0.ff.net.0.proj.bias, down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_k.weight, down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_k.weight, down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_out.0.bias, up_blocks.3.attentions.1.transformer_blocks.0.ff.net.0.proj.bias, up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_v.weight, down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_k.weight, down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_v.weight, up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_out.0.weight, up_blocks.1.attentions.1.transformer_blocks.0.ff.net.0.proj.bias, down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_k.weight, up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_out.0.bias, down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_out.0.bias, down_blocks.0.attentions.0.transformer_blocks.0.ff.net.0.proj.weight, up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_out.0.weight, down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_q.weight, down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_out.0.bias, down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_q.weight, up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_out.0.weight, down_blocks.2.attentions.0.transformer_blocks.0.ff.net.0.proj.weight, down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_out.0.bias, up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_k.weight, down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_out.0.bias, up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_v.weight, up_blocks.3.attentions.2.transformer_blocks.0.ff.net.0.proj.bias, mid_block.attentions.0.transformer_blocks.0.attn2.to_q.weight, mid_block.attentions.0.transformer_blocks.0.attn2.to_out.0.weight, mid_block.attentions.0.transformer_blocks.0.attn1.to_v.weight, down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_k.weight, up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_k.weight, up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_out.0.bias, down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_k.weight, up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_q.weight, down_blocks.0.attentions.0.transformer_blocks.0.ff.net.0.proj.bias, up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_k.weight, up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_out.0.bias, up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_out.0.bias, up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_out.0.weight, up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_q.weight, down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_v.weight, up_blocks.1.attentions.0.transformer_blocks.0.ff.net.0.proj.weight, down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_out.0.weight, down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_out.0.weight, up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_q.weight, down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_q.weight, down_blocks.1.attentions.0.transformer_blocks.0.ff.net.0.proj.bias, down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_q.weight, up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_v.weight, down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_out.0.weight, down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_v.weight, down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_out.0.bias, down_blocks.1.attentions.1.transformer_blocks.0.ff.net.0.proj.weight, down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_v.weight, down_blocks.2.attentions.0.transformer_blocks.0.ff.net.0.proj.bias, up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_q.weight, up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_out.0.weight, down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_v.weight, mid_block.attentions.0.transformer_blocks.0.attn2.to_out.0.bias, down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_k.weight, down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_out.0.bias. Please make sure to pass low_cpu_mem_usage=Falseanddevice_map=None if you want to randomly initialize those weights or else make sure your checkpoint file is correct.

and dreambooth using Lora doesn't work, how to deal with it?

Jun 05 '23 08:06 fitmos

After DAYS of research and failed attempts, I finally got it working! :))))))

Heres what I did:

I did as the error states to do: "Please make sure to pass low_cpu_mem_usage=False and device_map=None if you want to randomly initialize those weights"

I edited the file "Path_To_Stable_Diffusion/extensions/sd_dreambooth_extension-xxx/dreambooth/train_dreambooth.py" to contain this (now im no python professional, but I somehow made it work)

if is_torch_version(">=", "1.9.0"): _LOW_CPU_MEM_USAGE_DEFAULT = False else: _LOW_CPU_MEM_USAGE_DEFAULT = False

import accelerate from accelerate.utils import set_module_tensor_to_device from accelerate.utils.versions import is_torch_version from accelerate import load_checkpoint_and_dispatch

def model(load_checkpoint_and_dispatch): model, checkpoint=checkpoint_file, device_map="none"

Oh and Also: in Dreambooth, set "Save Model Frequency (Epochs)" to 0 and also set "Save Preview(s) Frequency (Epochs) " to 0 as well. This fixes the "missing weights" error by initializing them, but only doing so once... I encountered another error previously because it tried to initialize the weights more than once (with each save), so setting Dreambooth to only save at the end of training worked.

I hope this helps somebody out!

Dec 17 '23 19:12 vanguard1097