gradio_app/custom_models/image2mvimage.yaml

pretrained_model_name_or_path: "./ckpt/img2mvimg"
mixed_precision: "bf16"

init_config: 
  # enable controls
  enable_cross_attn_lora: False
  enable_cross_attn_ip: False
  enable_self_attn_lora: False
  enable_self_attn_ref: False
  enable_multiview_attn: True

  # for cross attention
  init_cross_attn_lora: False
  init_cross_attn_ip: False
  cross_attn_lora_rank: 256        # 0 for not enabled
  cross_attn_lora_only_kv: False
  ipadapter_pretrained_name: "h94/IP-Adapter"
  ipadapter_subfolder_name: "models"
  ipadapter_weight_name: "ip-adapter_sd15.safetensors"
  ipadapter_effect_on: "all"    # all, first

  # for self attention
  init_self_attn_lora: False
  self_attn_lora_rank: 256
  self_attn_lora_only_kv: False

  # for self attention ref
  init_self_attn_ref: False
  self_attn_ref_position: "attn1"
  self_attn_ref_other_model_name: "lambdalabs/sd-image-variations-diffusers"
  self_attn_ref_pixel_wise_crosspond: False
  self_attn_ref_effect_on: "all"
  
  # for multiview attention
  init_multiview_attn: True
  multiview_attn_position: "attn1"
  use_mv_joint_attn: True
  num_modalities: 1
  
  # for unet
  init_unet_path: "${pretrained_model_name_or_path}"
  cat_condition: True       # cat condition to input
  
  # for cls embedding
  init_num_cls_label: 8     # for initialize
  cls_labels: [0, 1, 2, 3]  # for current task

trainers:
  - trainer_type: "image2mvimage_trainer"
    trainer:
        pretrained_model_name_or_path: "${pretrained_model_name_or_path}"
        attn_config:
          cls_labels: [0, 1, 2, 3]  # for current task
          enable_cross_attn_lora: False
          enable_cross_attn_ip: False
          enable_self_attn_lora: False
          enable_self_attn_ref: False
          enable_multiview_attn: True
        resolution: "256"
        condition_image_resolution: "256"
        normal_cls_offset: 4
        condition_image_column_name: "conditioning_image"
        image_column_name: "image"