|
{ |
|
"_class_name": "UNet2DConditionModel", |
|
"_commit_hash": null, |
|
"_diffusers_version": "0.26.3", |
|
"_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--SG161222--RealVisXL_V4.0_Lightning/snapshots/33e9d9d5942df0ae0d07906e6c5aac2bad6f465f/unet", |
|
"_use_default_values": [ |
|
"attention_type", |
|
"reverse_transformer_layers_per_block", |
|
"dropout" |
|
], |
|
"act_fn": "silu", |
|
"addition_embed_type": "text_time", |
|
"addition_embed_type_num_heads": 64, |
|
"addition_time_embed_dim": 256, |
|
"attention_head_dim": [ |
|
5, |
|
10, |
|
20 |
|
], |
|
"attention_type": "default", |
|
"block_out_channels": [ |
|
320, |
|
640, |
|
1280 |
|
], |
|
"center_input_sample": false, |
|
"class_embed_type": null, |
|
"class_embeddings_concat": false, |
|
"conv_in_kernel": 3, |
|
"conv_out_kernel": 3, |
|
"cross_attention_dim": 2048, |
|
"cross_attention_norm": null, |
|
"down_block_types": [ |
|
"DownBlock2D", |
|
"CrossAttnDownBlock2D", |
|
"CrossAttnDownBlock2D" |
|
], |
|
"downsample_padding": 1, |
|
"dropout": 0.0, |
|
"dual_cross_attention": false, |
|
"encoder_hid_dim": null, |
|
"encoder_hid_dim_type": null, |
|
"flip_sin_to_cos": true, |
|
"freq_shift": 0, |
|
"in_channels": 4, |
|
"layers_per_block": 2, |
|
"mid_block_only_cross_attention": null, |
|
"mid_block_scale_factor": 1, |
|
"mid_block_type": "UNetMidBlock2DCrossAttn", |
|
"neuron": { |
|
"auto_cast": "matmul", |
|
"auto_cast_type": "bf16", |
|
"compiler_type": "neuronx-cc", |
|
"compiler_version": "2.13.66.0+6dfecc895", |
|
"dynamic_batch_size": false, |
|
"inline_weights_to_neff": true, |
|
"input_names": [ |
|
"sample", |
|
"timestep", |
|
"encoder_hidden_states", |
|
"text_embeds", |
|
"time_ids" |
|
], |
|
"model_type": "unet", |
|
"optlevel": "2", |
|
"output_attentions": false, |
|
"output_hidden_states": false, |
|
"output_names": [ |
|
"sample" |
|
], |
|
"static_batch_size": 1, |
|
"static_height": 128, |
|
"static_num_channels": 4, |
|
"static_sequence_length": 77, |
|
"static_width": 128 |
|
}, |
|
"norm_eps": 1e-05, |
|
"norm_num_groups": 32, |
|
"num_attention_heads": null, |
|
"num_class_embeds": null, |
|
"only_cross_attention": false, |
|
"out_channels": 4, |
|
"projection_class_embeddings_input_dim": 2816, |
|
"resnet_out_scale_factor": 1.0, |
|
"resnet_skip_time_act": false, |
|
"resnet_time_scale_shift": "default", |
|
"reverse_transformer_layers_per_block": null, |
|
"sample_size": 128, |
|
"task": "semantic-segmentation", |
|
"time_cond_proj_dim": null, |
|
"time_embedding_act_fn": null, |
|
"time_embedding_dim": null, |
|
"time_embedding_type": "positional", |
|
"timestep_post_act": null, |
|
"transformer_layers_per_block": [ |
|
1, |
|
2, |
|
10 |
|
], |
|
"transformers_version": null, |
|
"up_block_types": [ |
|
"CrossAttnUpBlock2D", |
|
"CrossAttnUpBlock2D", |
|
"UpBlock2D" |
|
], |
|
"upcast_attention": null, |
|
"use_linear_projection": true |
|
} |
|
|