AttributeError: 'CrossAttention' object has no attribute 'reshape_heads_to_batch_dim'

[xiaqingsun]

Has anyone encountered this problem “AttributeError: 'CrossAttention' object has no attribute 'reshape_heads_to_batch_dim' ”

[nupurkmr9]

Hi, pip install diffuser==0.11 should solve the problem for now. I will update the code soon to support the new version of diffuser library.

Thanks.

[xiaqingsun]

Thanks for your answer, it worked with diffuser==0.11. The results I reproduced with the data in the paper are good

my input images:

my result:

But I change other pictures, the result is worse（the sunglasses is not like my input sunglasses）

my input images:

my result:

My training parameters are as follows：（I use the pretrained_model: runwayml/stable-diffusion-v1-5）

!accelerate launch src/diffuser_training.py \ --pretrained_model_name_or_path=$MODEL_NAME \ --output_dir=$OUTPUT_DIR \ --concepts_list="/content/concepts_list.json" \ --with_prior_preservation --prior_loss_weight=1.0 \ --resolution=512 \ --train_batch_size=2 \ --learning_rate=1e-5 \ --lr_warmup_steps=0 \ --max_train_steps=500 \ --num_class_images=200 \ --scale_lr --hflip \ --modifier_token "\<whxm>+\<bkmj>"

My concept_list.json are as follows:

Is there something wrong with my training process causing this poor result？ Looking forward for your reply, thank you！ @nupurkmr9

[wangzhaolei]

Are you missing an s after diffuser，that is pip install diffusers==0.11，

[yannqi]

Another feasible way, you can change 'reshape_heads_to_batch_dim' to 'head_to_batch_dim' According to https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py