{ "spatial_dims": 3, "image_channels": 1, "latent_channels": 4, "include_body_region": true, "mask_generation_latent_shape": [ 4, 64, 64, 64 ], "autoencoder_def": { "_target_": "monai.apps.generation.maisi.networks.autoencoderkl_maisi.AutoencoderKlMaisi", "spatial_dims": "@spatial_dims", "in_channels": "@image_channels", "out_channels": "@image_channels", "latent_channels": "@latent_channels", "num_channels": [ 64, 128, 256 ], "num_res_blocks": [2,2,2], "norm_num_groups": 32, "norm_eps": 1e-06, "attention_levels": [ false, false, false ], "with_encoder_nonlocal_attn": false, "with_decoder_nonlocal_attn": false, "use_checkpointing": false, "use_convtranspose": false, "norm_float16": true, "num_splits": 8, "dim_split": 1 }, "diffusion_unet_def": { "_target_": "monai.apps.generation.maisi.networks.diffusion_model_unet_maisi.DiffusionModelUNetMaisi", "spatial_dims": "@spatial_dims", "in_channels": "@latent_channels", "out_channels": "@latent_channels", "num_channels": [ 64, 128, 256, 512 ], "attention_levels": [ false, false, true, true ], "num_head_channels": [ 0, 0, 32, 32 ], "num_res_blocks": 2, "use_flash_attention": true, "include_top_region_index_input": "@include_body_region", "include_bottom_region_index_input": "@include_body_region", "include_spacing_input": true, "include_fc": false, "resblock_updown": false }, "controlnet_def": { "_target_": "monai.apps.generation.maisi.networks.controlnet_maisi.ControlNetMaisi", "spatial_dims": "@spatial_dims", "in_channels": "@latent_channels", "num_channels": [ 64, 128, 256, 512 ], "attention_levels": [ false, false, true, true ], "num_head_channels": [ 0, 0, 32, 32 ], "num_res_blocks": 2, "use_flash_attention": true, "conditioning_embedding_in_channels": 8, "conditioning_embedding_num_channels": [8, 32, 64], "include_fc": false, "resblock_updown": false }, "mask_generation_autoencoder_def": { "_target_": "monai.apps.generation.maisi.networks.autoencoderkl_maisi.AutoencoderKlMaisi", "spatial_dims": "@spatial_dims", "in_channels": 8, "out_channels": 125, "latent_channels": "@latent_channels", "num_channels": [ 32, 64, 128 ], "num_res_blocks": [1, 2, 2], "norm_num_groups": 32, "norm_eps": 1e-06, "attention_levels": [ false, false, false ], "with_encoder_nonlocal_attn": false, "with_decoder_nonlocal_attn": false, "use_flash_attention": false, "use_checkpointing": true, "use_convtranspose": true, "norm_float16": true, "num_splits": 8, "dim_split": 1 }, "mask_generation_diffusion_def": { "_target_": "monai.networks.nets.diffusion_model_unet.DiffusionModelUNet", "spatial_dims": "@spatial_dims", "in_channels": "@latent_channels", "out_channels": "@latent_channels", "channels":[64, 128, 256, 512], "attention_levels":[false, false, true, true], "num_head_channels":[0, 0, 32, 32], "num_res_blocks": 2, "use_flash_attention": true, "with_conditioning": true, "upcast_attention": true, "cross_attention_dim": 10 }, "mask_generation_scale_factor": 1.0055984258651733, "noise_scheduler": { "_target_": "monai.networks.schedulers.ddpm.DDPMScheduler", "num_train_timesteps": 1000, "beta_start": 0.0015, "beta_end": 0.0195, "schedule": "scaled_linear_beta", "clip_sample": false }, "mask_generation_noise_scheduler": { "_target_": "monai.networks.schedulers.ddpm.DDPMScheduler", "num_train_timesteps": 1000, "beta_start": 0.0015, "beta_end": 0.0195, "schedule": "scaled_linear_beta", "clip_sample": false } }