OchiaiNao

You can add these images manually with the following structure: ```bash your_class_data_dir ├── images │ ├── 01.jpg │ ├── 02.jpg ├── caption.txt # captions line by line └── images.txt #...

Hi, this is my test train code: ```Python accelerate launch train_custom_diffusion.py \ --pretrained_model_name_or_path=CompVis/stable-diffusion-v1-4 \ --instance_data_dir=/content/drive/MyDrive/diffusion/class_woman/young_woman \ --output_dir=/content/drive/MyDrive/diffusion/train_logs/young_woman \ --class_data_dir=/content/drive/MyDrive/diffusion/real_woman/ \ --with_prior_preservation --real_prior --prior_loss_weight=1.0 \ --instance_prompt="photo of a woman" \ --class_prompt='woman'...

Hi, I used what you mentioned to load new text embeddings, e.g. \. But when it goes to show cross-attention process: ```Python prompts = [prompt] controller = AttentionStore() image_inv, x_t...