3 lines
2.4 KiB
Python
3 lines
2.4 KiB
Python
{'sample_size': 64, 'in_channels': 4, 'down_block_types': ('CrossAttnDownBlock2D', 'CrossAttnDownBlock2D', 'CrossAttnDownBlock2D', 'DownBlock2D'), 'block_out_channels': (320, 640, 1280, 1280), 'layers_per_block': 2, 'cross_attention_dim': 768, 'attention_head_dim': 8, 'use_linear_projection': False, 'class_embed_type': None, 'addition_embed_type': None, 'addition_time_embed_dim': None, 'projection_class_embeddings_input_dim': None, 'transformer_layers_per_block': 1, 'out_channels': 4, 'up_block_types': ('UpBlock2D', 'CrossAttnUpBlock2D', 'CrossAttnUpBlock2D', 'CrossAttnUpBlock2D')}
|
|
'sample_size', 64), ('in_channels', 4), ('out_channels', 4), ('center_input_sample', False), ('flip_sin_to_cos', True), ('freq_shift', 0), ('down_block_types', ['CrossAttnDownBlock3D', 'CrossAttnDownBlock3D', 'CrossAttnDownBlock3D', 'DownBlock3D']), ('mid_block_type', 'UNetMidBlock3DCrossAttn'), ('up_block_types', ['UpBlock3D', 'CrossAttnUpBlock3D', 'CrossAttnUpBlock3D', 'CrossAttnUpBlock3D']), ('only_cross_attention', False), ('block_out_channels', [320, 640, 1280, 1280]), ('layers_per_block', 2), ('downsample_padding', 1), ('mid_block_scale_factor', 1), ('act_fn', 'silu'), ('norm_num_groups', 32), ('norm_eps', 1e-05), ('cross_attention_dim', 768), ('attention_head_dim', 8), ('dual_cross_attention', False), ('use_linear_projection', False), ('class_embed_type', None), ('num_class_embeds', None), ('upcast_attention', False), ('resnet_time_scale_shift', 'default'), ('use_inflated_groupnorm', True), ('use_motion_module', True), ('motion_module_resolutions', [1, 2, 4, 8]), ('motion_module_mid_block', False), ('motion_module_decoder_only', False), ('motion_module_type', 'Vanilla'), ('motion_module_kwargs', {'num_attention_heads': 8, 'num_transformer_block': 1, 'attention_block_types': ['Temporal_Self', 'Temporal_Self'], 'temporal_position_encoding': True, 'temporal_position_encoding_max_len': 32, 'temporal_attention_dim_div': 1, 'zero_initialize': True}), ('unet_use_cross_frame_attention', False), ('unet_use_temporal_attention', False), ('_use_default_values', ['resnet_time_scale_shift', 'only_cross_attention', 'mid_block_type', 'unet_use_cross_frame_attention', 'class_embed_type', 'unet_use_temporal_attention', 'dual_cross_attention', 'num_class_embeds', 'upcast_attention', 'use_linear_projection', 'motion_module_decoder_only']), ('_class_name', 'UNet3DConditionModel'), ('_diffusers_version', '0.6.0')])
|
|
|