Upload 26 files
Browse filesInitial submission
- checkpoint/.DS_Store +0 -0
- checkpoint/denoiser/config.json +141 -0
- checkpoint/denoiser/diffusion_pytorch_model.safetensors +3 -0
- checkpoint/denoiser_garment/config.json +139 -0
- checkpoint/denoiser_garment/diffusion_pytorch_model.safetensors +3 -0
- checkpoint/image_encoder/config.json +48 -0
- checkpoint/image_encoder/model.safetensors +3 -0
- checkpoint/image_encoder/preprocessor_config.json +27 -0
- checkpoint/model_index.json +48 -0
- checkpoint/scheduler/scheduler_config.json +16 -0
- checkpoint/text_encoder/config.json +25 -0
- checkpoint/text_encoder/model.safetensors +3 -0
- checkpoint/text_encoder_2/config.json +25 -0
- checkpoint/text_encoder_2/model.safetensors +3 -0
- checkpoint/tokenizer/merges.txt +0 -0
- checkpoint/tokenizer/special_tokens_map.json +30 -0
- checkpoint/tokenizer/tokenizer_config.json +30 -0
- checkpoint/tokenizer/vocab.json +0 -0
- checkpoint/tokenizer_2/merges.txt +0 -0
- checkpoint/tokenizer_2/special_tokens_map.json +30 -0
- checkpoint/tokenizer_2/tokenizer_config.json +38 -0
- checkpoint/tokenizer_2/vocab.json +0 -0
- checkpoint/vae/config.json +38 -0
- checkpoint/vae/diffusion_pytorch_model.safetensors +3 -0
- checkpoint/vae_decoder/decoder.json +47 -0
- checkpoint/vae_decoder/decoder.pt +3 -0
checkpoint/.DS_Store
ADDED
|
Binary file (6.15 kB). View file
|
|
|
checkpoint/denoiser/config.json
ADDED
|
@@ -0,0 +1,141 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.32.2",
|
| 4 |
+
"_name_or_path": "/data02/zhenchen/VTO_mobile/result/cat_final/checkpoint-8280",
|
| 5 |
+
"act_fn": "hardswish",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": 256,
|
| 9 |
+
"attention_head_dim": [
|
| 10 |
+
4,
|
| 11 |
+
8,
|
| 12 |
+
14
|
| 13 |
+
],
|
| 14 |
+
"attention_type": "default",
|
| 15 |
+
"attn_module": "Attention",
|
| 16 |
+
"attn_processor_type": "AttnProcessor2_0",
|
| 17 |
+
"block_out_channels": [
|
| 18 |
+
256,
|
| 19 |
+
512,
|
| 20 |
+
896
|
| 21 |
+
],
|
| 22 |
+
"center_input_sample": false,
|
| 23 |
+
"class_embed_type": null,
|
| 24 |
+
"class_embeddings_concat": false,
|
| 25 |
+
"context_embedding_caption_projection_dim": 2048,
|
| 26 |
+
"context_embedding_text_embedding_dim": 4096,
|
| 27 |
+
"conv_in_dw_bias": true,
|
| 28 |
+
"conv_in_kernel": 3,
|
| 29 |
+
"conv_in_module": "Conv2d",
|
| 30 |
+
"conv_in_pw_bias": false,
|
| 31 |
+
"conv_out_dw_bias": true,
|
| 32 |
+
"conv_out_kernel": 3,
|
| 33 |
+
"conv_out_module": "Conv2d",
|
| 34 |
+
"conv_out_pw_bias": false,
|
| 35 |
+
"cross_attention_dim": 4096,
|
| 36 |
+
"cross_attention_norm": null,
|
| 37 |
+
"down_block_ff_mult": 3,
|
| 38 |
+
"down_block_kv_heads": 1,
|
| 39 |
+
"down_block_qk_norm": "layer_norm",
|
| 40 |
+
"down_block_resnet_dw_bias": true,
|
| 41 |
+
"down_block_resnet_middle_expansion": 2,
|
| 42 |
+
"down_block_resnet_middle_expansion_type": "input",
|
| 43 |
+
"down_block_resnet_pw_bias": false,
|
| 44 |
+
"down_block_types": [
|
| 45 |
+
"CrossAttnDownBlock2D",
|
| 46 |
+
"CrossAttnDownBlock2D",
|
| 47 |
+
"CrossAttnDownBlock2D"
|
| 48 |
+
],
|
| 49 |
+
"down_block_use_self_attention": [
|
| 50 |
+
false,
|
| 51 |
+
false,
|
| 52 |
+
true
|
| 53 |
+
],
|
| 54 |
+
"downsample_conv_module": "SepConv2d",
|
| 55 |
+
"downsample_module": "Downsample2D",
|
| 56 |
+
"downsample_padding": 1,
|
| 57 |
+
"dropout": 0.0,
|
| 58 |
+
"dual_cross_attention": false,
|
| 59 |
+
"encoder_hid_dim": null,
|
| 60 |
+
"encoder_hid_dim_type": "ip_image_proj",
|
| 61 |
+
"encoder_type": "dinov2_base",
|
| 62 |
+
"flip_sin_to_cos": true,
|
| 63 |
+
"freq_shift": 0,
|
| 64 |
+
"height": 2048,
|
| 65 |
+
"in_channels": 32,
|
| 66 |
+
"layers_per_block": 2,
|
| 67 |
+
"mid_block_ff_mult": 3,
|
| 68 |
+
"mid_block_kv_heads": 1,
|
| 69 |
+
"mid_block_only_cross_attention": null,
|
| 70 |
+
"mid_block_qk_norm": "layer_norm",
|
| 71 |
+
"mid_block_resnet_dw_bias": true,
|
| 72 |
+
"mid_block_resnet_middle_expansion": 2,
|
| 73 |
+
"mid_block_resnet_middle_expansion_type": "input",
|
| 74 |
+
"mid_block_resnet_pw_bias": false,
|
| 75 |
+
"mid_block_scale_factor": 1,
|
| 76 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 77 |
+
"mid_block_use_additional_resnet": false,
|
| 78 |
+
"mid_block_use_self_attention": true,
|
| 79 |
+
"norm_eps": 1e-05,
|
| 80 |
+
"norm_num_groups": 32,
|
| 81 |
+
"num_attention_heads": null,
|
| 82 |
+
"num_class_embeds": null,
|
| 83 |
+
"only_cross_attention": false,
|
| 84 |
+
"out_channels": 16,
|
| 85 |
+
"pooled_projection_dim": 2048,
|
| 86 |
+
"projection_class_embeddings_input_dim": 2816,
|
| 87 |
+
"resnet_conv_module": "SepConv2d",
|
| 88 |
+
"resnet_module": "ResnetBlock2D",
|
| 89 |
+
"resnet_out_scale_factor": 1.0,
|
| 90 |
+
"resnet_skip_time_act": false,
|
| 91 |
+
"resnet_time_scale_shift": "default",
|
| 92 |
+
"reverse_transformer_layers_per_block": null,
|
| 93 |
+
"sample_size": 128,
|
| 94 |
+
"time_cond_proj_dim": null,
|
| 95 |
+
"time_embedding_act_fn": null,
|
| 96 |
+
"time_embedding_dim": null,
|
| 97 |
+
"time_embedding_module": "TimestepEmbedding",
|
| 98 |
+
"time_embedding_type": "positional",
|
| 99 |
+
"time_text_embedding_act_fn": "hardswish",
|
| 100 |
+
"time_text_embedding_mode": "default",
|
| 101 |
+
"time_text_embedding_module": "CombinedTimestepTextProjEmbeddings",
|
| 102 |
+
"time_text_embedding_pooled_projection_dim": 2048,
|
| 103 |
+
"time_text_embedding_time_embed_dim": 896,
|
| 104 |
+
"timestep_post_act": null,
|
| 105 |
+
"transformer2d_model_type": "Transformer2DModel",
|
| 106 |
+
"transformer_block_type": "BasicTransformerBlockTryOn",
|
| 107 |
+
"transformer_layers_per_block": [
|
| 108 |
+
1,
|
| 109 |
+
2,
|
| 110 |
+
4
|
| 111 |
+
],
|
| 112 |
+
"up_block_ff_mult": 3,
|
| 113 |
+
"up_block_kv_heads": 1,
|
| 114 |
+
"up_block_qk_norm": "layer_norm",
|
| 115 |
+
"up_block_receive_additional_residuals": [
|
| 116 |
+
false,
|
| 117 |
+
true,
|
| 118 |
+
true
|
| 119 |
+
],
|
| 120 |
+
"up_block_resnet_dw_bias": true,
|
| 121 |
+
"up_block_resnet_middle_expansion": 2,
|
| 122 |
+
"up_block_resnet_middle_expansion_type": "input",
|
| 123 |
+
"up_block_resnet_pw_bias": false,
|
| 124 |
+
"up_block_types": [
|
| 125 |
+
"CrossAttnUpBlock2D",
|
| 126 |
+
"CrossAttnUpBlock2D",
|
| 127 |
+
"UpBlock2D"
|
| 128 |
+
],
|
| 129 |
+
"up_block_use_self_attention": [
|
| 130 |
+
true,
|
| 131 |
+
false,
|
| 132 |
+
false
|
| 133 |
+
],
|
| 134 |
+
"upcast_attention": null,
|
| 135 |
+
"upsample_conv_module": "SepConv2d",
|
| 136 |
+
"upsample_module": "Upsample2D",
|
| 137 |
+
"use_linear_projection": true,
|
| 138 |
+
"use_pooled_projection": false,
|
| 139 |
+
"use_rope": true,
|
| 140 |
+
"width": 768
|
| 141 |
+
}
|
checkpoint/denoiser/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34ee9331e414a8d89ebd8c4c485094947f1fa710ef34d40a7726a623a7f3eca2
|
| 3 |
+
size 840173776
|
checkpoint/denoiser_garment/config.json
ADDED
|
@@ -0,0 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.32.2",
|
| 4 |
+
"act_fn": "hardswish",
|
| 5 |
+
"addition_embed_type": null,
|
| 6 |
+
"addition_embed_type_num_heads": 64,
|
| 7 |
+
"addition_time_embed_dim": 256,
|
| 8 |
+
"attention_head_dim": [
|
| 9 |
+
4,
|
| 10 |
+
8,
|
| 11 |
+
14
|
| 12 |
+
],
|
| 13 |
+
"attention_type": "default",
|
| 14 |
+
"attn_module": "Attention",
|
| 15 |
+
"attn_processor_type": "AttnProcessor2_0",
|
| 16 |
+
"block_out_channels": [
|
| 17 |
+
256,
|
| 18 |
+
512,
|
| 19 |
+
896
|
| 20 |
+
],
|
| 21 |
+
"center_input_sample": false,
|
| 22 |
+
"class_embed_type": null,
|
| 23 |
+
"class_embeddings_concat": false,
|
| 24 |
+
"context_embedding_caption_projection_dim": 2048,
|
| 25 |
+
"context_embedding_text_embedding_dim": 4096,
|
| 26 |
+
"conv_in_dw_bias": true,
|
| 27 |
+
"conv_in_kernel": 3,
|
| 28 |
+
"conv_in_module": "Conv2d",
|
| 29 |
+
"conv_in_pw_bias": false,
|
| 30 |
+
"conv_out_dw_bias": true,
|
| 31 |
+
"conv_out_kernel": 3,
|
| 32 |
+
"conv_out_module": "Conv2d",
|
| 33 |
+
"conv_out_pw_bias": false,
|
| 34 |
+
"cross_attention_dim": 4096,
|
| 35 |
+
"cross_attention_norm": null,
|
| 36 |
+
"down_block_ff_mult": 3,
|
| 37 |
+
"down_block_kv_heads": 1,
|
| 38 |
+
"down_block_qk_norm": "layer_norm",
|
| 39 |
+
"down_block_resnet_dw_bias": true,
|
| 40 |
+
"down_block_resnet_middle_expansion": 2,
|
| 41 |
+
"down_block_resnet_middle_expansion_type": "input",
|
| 42 |
+
"down_block_resnet_pw_bias": false,
|
| 43 |
+
"down_block_types": [
|
| 44 |
+
"CrossAttnDownBlock2D",
|
| 45 |
+
"CrossAttnDownBlock2D",
|
| 46 |
+
"CrossAttnDownBlock2D"
|
| 47 |
+
],
|
| 48 |
+
"down_block_use_self_attention": [
|
| 49 |
+
false,
|
| 50 |
+
false,
|
| 51 |
+
true
|
| 52 |
+
],
|
| 53 |
+
"downsample_conv_module": "SepConv2d",
|
| 54 |
+
"downsample_module": "Downsample2D",
|
| 55 |
+
"downsample_padding": 1,
|
| 56 |
+
"dropout": 0.0,
|
| 57 |
+
"dual_cross_attention": false,
|
| 58 |
+
"encoder_hid_dim": null,
|
| 59 |
+
"encoder_hid_dim_type": null,
|
| 60 |
+
"flip_sin_to_cos": true,
|
| 61 |
+
"freq_shift": 0,
|
| 62 |
+
"height": 1024,
|
| 63 |
+
"in_channels": 16,
|
| 64 |
+
"layers_per_block": 2,
|
| 65 |
+
"mid_block_ff_mult": 3,
|
| 66 |
+
"mid_block_kv_heads": 1,
|
| 67 |
+
"mid_block_only_cross_attention": null,
|
| 68 |
+
"mid_block_qk_norm": "layer_norm",
|
| 69 |
+
"mid_block_resnet_dw_bias": true,
|
| 70 |
+
"mid_block_resnet_middle_expansion": 2,
|
| 71 |
+
"mid_block_resnet_middle_expansion_type": "input",
|
| 72 |
+
"mid_block_resnet_pw_bias": false,
|
| 73 |
+
"mid_block_scale_factor": 1,
|
| 74 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 75 |
+
"mid_block_use_additional_resnet": false,
|
| 76 |
+
"mid_block_use_self_attention": true,
|
| 77 |
+
"norm_eps": 1e-05,
|
| 78 |
+
"norm_num_groups": 32,
|
| 79 |
+
"num_attention_heads": null,
|
| 80 |
+
"num_class_embeds": null,
|
| 81 |
+
"only_cross_attention": false,
|
| 82 |
+
"out_channels": 16,
|
| 83 |
+
"pooled_projection_dim": 2048,
|
| 84 |
+
"projection_class_embeddings_input_dim": 2816,
|
| 85 |
+
"resnet_conv_module": "SepConv2d",
|
| 86 |
+
"resnet_module": "ResnetBlock2D",
|
| 87 |
+
"resnet_out_scale_factor": 1.0,
|
| 88 |
+
"resnet_skip_time_act": false,
|
| 89 |
+
"resnet_time_scale_shift": "default",
|
| 90 |
+
"reverse_transformer_layers_per_block": null,
|
| 91 |
+
"sample_size": 128,
|
| 92 |
+
"time_cond_proj_dim": null,
|
| 93 |
+
"time_embedding_act_fn": null,
|
| 94 |
+
"time_embedding_dim": null,
|
| 95 |
+
"time_embedding_module": "TimestepEmbedding",
|
| 96 |
+
"time_embedding_type": "positional",
|
| 97 |
+
"time_text_embedding_act_fn": "hardswish",
|
| 98 |
+
"time_text_embedding_mode": "default",
|
| 99 |
+
"time_text_embedding_module": "CombinedTimestepTextProjEmbeddings",
|
| 100 |
+
"time_text_embedding_pooled_projection_dim": 2048,
|
| 101 |
+
"time_text_embedding_time_embed_dim": 896,
|
| 102 |
+
"timestep_post_act": null,
|
| 103 |
+
"transformer2d_model_type": "Transformer2DModel",
|
| 104 |
+
"transformer_block_type": "BasicTransformerBlockGarment",
|
| 105 |
+
"transformer_layers_per_block": [
|
| 106 |
+
1,
|
| 107 |
+
2,
|
| 108 |
+
4
|
| 109 |
+
],
|
| 110 |
+
"up_block_ff_mult": 3,
|
| 111 |
+
"up_block_kv_heads": 1,
|
| 112 |
+
"up_block_qk_norm": "layer_norm",
|
| 113 |
+
"up_block_receive_additional_residuals": [
|
| 114 |
+
false,
|
| 115 |
+
true,
|
| 116 |
+
true
|
| 117 |
+
],
|
| 118 |
+
"up_block_resnet_dw_bias": true,
|
| 119 |
+
"up_block_resnet_middle_expansion": 2,
|
| 120 |
+
"up_block_resnet_middle_expansion_type": "input",
|
| 121 |
+
"up_block_resnet_pw_bias": false,
|
| 122 |
+
"up_block_types": [
|
| 123 |
+
"CrossAttnUpBlock2D",
|
| 124 |
+
"CrossAttnUpBlock2D",
|
| 125 |
+
"UpBlock2D"
|
| 126 |
+
],
|
| 127 |
+
"up_block_use_self_attention": [
|
| 128 |
+
true,
|
| 129 |
+
false,
|
| 130 |
+
false
|
| 131 |
+
],
|
| 132 |
+
"upcast_attention": null,
|
| 133 |
+
"upsample_conv_module": "SepConv2d",
|
| 134 |
+
"upsample_module": "Upsample2D",
|
| 135 |
+
"use_linear_projection": true,
|
| 136 |
+
"use_pooled_projection": false,
|
| 137 |
+
"use_rope": true,
|
| 138 |
+
"width": 768
|
| 139 |
+
}
|
checkpoint/denoiser_garment/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:902e5f6d47e9aef909497d5d7d400dd51cb39764fac63aca1e5b730927e53184
|
| 3 |
+
size 759200976
|
checkpoint/image_encoder/config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "../dinov2_base",
|
| 3 |
+
"apply_layernorm": true,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"Dinov2Model"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.0,
|
| 8 |
+
"drop_path_rate": 0.0,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.0,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"image_size": 518,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"layer_norm_eps": 1e-06,
|
| 15 |
+
"layerscale_value": 1.0,
|
| 16 |
+
"mlp_ratio": 4,
|
| 17 |
+
"model_type": "dinov2",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_channels": 3,
|
| 20 |
+
"num_hidden_layers": 12,
|
| 21 |
+
"out_features": [
|
| 22 |
+
"stage12"
|
| 23 |
+
],
|
| 24 |
+
"out_indices": [
|
| 25 |
+
12
|
| 26 |
+
],
|
| 27 |
+
"patch_size": 14,
|
| 28 |
+
"qkv_bias": true,
|
| 29 |
+
"reshape_hidden_states": true,
|
| 30 |
+
"stage_names": [
|
| 31 |
+
"stem",
|
| 32 |
+
"stage1",
|
| 33 |
+
"stage2",
|
| 34 |
+
"stage3",
|
| 35 |
+
"stage4",
|
| 36 |
+
"stage5",
|
| 37 |
+
"stage6",
|
| 38 |
+
"stage7",
|
| 39 |
+
"stage8",
|
| 40 |
+
"stage9",
|
| 41 |
+
"stage10",
|
| 42 |
+
"stage11",
|
| 43 |
+
"stage12"
|
| 44 |
+
],
|
| 45 |
+
"torch_dtype": "bfloat16",
|
| 46 |
+
"transformers_version": "4.42.0",
|
| 47 |
+
"use_swiglu_ffn": false
|
| 48 |
+
}
|
checkpoint/image_encoder/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a39e985dd10fd1ae72faa49c35ad211a17dc0457ebe7dcbe7b32b92da4007506
|
| 3 |
+
size 173185040
|
checkpoint/image_encoder/preprocessor_config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": {
|
| 3 |
+
"height": 224,
|
| 4 |
+
"width": 224
|
| 5 |
+
},
|
| 6 |
+
"do_center_crop": true,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"image_mean": [
|
| 12 |
+
0.485,
|
| 13 |
+
0.456,
|
| 14 |
+
0.406
|
| 15 |
+
],
|
| 16 |
+
"image_processor_type": "BitImageProcessor",
|
| 17 |
+
"image_std": [
|
| 18 |
+
0.229,
|
| 19 |
+
0.224,
|
| 20 |
+
0.225
|
| 21 |
+
],
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"shortest_edge": 256
|
| 26 |
+
}
|
| 27 |
+
}
|
checkpoint/model_index.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "T2IMobilePipelineV1_3_NotLoadingT5_Decoder",
|
| 3 |
+
"_diffusers_version": "0.32.2",
|
| 4 |
+
"denoiser": [
|
| 5 |
+
"Mobile_VTON.models.unets.unet_2d_condition_tryon",
|
| 6 |
+
"UNet2DConditionModel"
|
| 7 |
+
],
|
| 8 |
+
"denoiser_garment": [
|
| 9 |
+
"Mobile_VTON.models.unets.unet_2d_condition_garment",
|
| 10 |
+
"UNet2DConditionModel"
|
| 11 |
+
],
|
| 12 |
+
"feature_extractor": [
|
| 13 |
+
null,
|
| 14 |
+
null
|
| 15 |
+
],
|
| 16 |
+
"image_encoder": [
|
| 17 |
+
"transformers",
|
| 18 |
+
"Dinov2Model"
|
| 19 |
+
],
|
| 20 |
+
"scheduler": [
|
| 21 |
+
"diffusers",
|
| 22 |
+
"FlowMatchEulerDiscreteScheduler"
|
| 23 |
+
],
|
| 24 |
+
"text_encoder": [
|
| 25 |
+
"transformers",
|
| 26 |
+
"CLIPTextModelWithProjection"
|
| 27 |
+
],
|
| 28 |
+
"text_encoder_2": [
|
| 29 |
+
"transformers",
|
| 30 |
+
"CLIPTextModelWithProjection"
|
| 31 |
+
],
|
| 32 |
+
"tokenizer": [
|
| 33 |
+
"transformers",
|
| 34 |
+
"CLIPTokenizer"
|
| 35 |
+
],
|
| 36 |
+
"tokenizer_2": [
|
| 37 |
+
"transformers",
|
| 38 |
+
"CLIPTokenizer"
|
| 39 |
+
],
|
| 40 |
+
"vae": [
|
| 41 |
+
"diffusers",
|
| 42 |
+
"AutoencoderKL"
|
| 43 |
+
],
|
| 44 |
+
"vae_decoder": [
|
| 45 |
+
null,
|
| 46 |
+
null
|
| 47 |
+
]
|
| 48 |
+
}
|
checkpoint/scheduler/scheduler_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "FlowMatchEulerDiscreteScheduler",
|
| 3 |
+
"_diffusers_version": "0.32.2",
|
| 4 |
+
"base_image_seq_len": 256,
|
| 5 |
+
"base_shift": 0.5,
|
| 6 |
+
"invert_sigmas": false,
|
| 7 |
+
"max_image_seq_len": 4096,
|
| 8 |
+
"max_shift": 1.15,
|
| 9 |
+
"num_train_timesteps": 1000,
|
| 10 |
+
"shift": 3.0,
|
| 11 |
+
"shift_terminal": null,
|
| 12 |
+
"use_beta_sigmas": false,
|
| 13 |
+
"use_dynamic_shifting": false,
|
| 14 |
+
"use_exponential_sigmas": false,
|
| 15 |
+
"use_karras_sigmas": false
|
| 16 |
+
}
|
checkpoint/text_encoder/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/data02/zhenchen/VTO_mobile/checkpoints/text_encoder",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPTextModelWithProjection"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"dropout": 0.0,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "quick_gelu",
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_factor": 1.0,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 77,
|
| 17 |
+
"model_type": "clip_text_model",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"projection_dim": 768,
|
| 22 |
+
"torch_dtype": "bfloat16",
|
| 23 |
+
"transformers_version": "4.42.0",
|
| 24 |
+
"vocab_size": 49408
|
| 25 |
+
}
|
checkpoint/text_encoder/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4ddf499861727e83713b525ba1e087202f248a7ebb2268b04d1de09de5b67c2
|
| 3 |
+
size 247324096
|
checkpoint/text_encoder_2/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/data02/zhenchen/VTO_mobile/checkpoints/text_encoder_2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPTextModelWithProjection"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"dropout": 0.0,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_size": 1280,
|
| 12 |
+
"initializer_factor": 1.0,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 5120,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 77,
|
| 17 |
+
"model_type": "clip_text_model",
|
| 18 |
+
"num_attention_heads": 20,
|
| 19 |
+
"num_hidden_layers": 32,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"projection_dim": 1280,
|
| 22 |
+
"torch_dtype": "bfloat16",
|
| 23 |
+
"transformers_version": "4.42.0",
|
| 24 |
+
"vocab_size": 49408
|
| 25 |
+
}
|
checkpoint/text_encoder_2/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4ba596d8c78b5509aafd523f619e13aa129ae1a886a1e92766d7cddd9706f3c
|
| 3 |
+
size 1389382688
|
checkpoint/tokenizer/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint/tokenizer/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|startoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint/tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"49406": {
|
| 5 |
+
"content": "<|startoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"49407": {
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"bos_token": "<|startoftext|>",
|
| 22 |
+
"clean_up_tokenization_spaces": true,
|
| 23 |
+
"do_lower_case": true,
|
| 24 |
+
"eos_token": "<|endoftext|>",
|
| 25 |
+
"errors": "replace",
|
| 26 |
+
"model_max_length": 77,
|
| 27 |
+
"pad_token": "<|endoftext|>",
|
| 28 |
+
"tokenizer_class": "CLIPTokenizer",
|
| 29 |
+
"unk_token": "<|endoftext|>"
|
| 30 |
+
}
|
checkpoint/tokenizer/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint/tokenizer_2/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint/tokenizer_2/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|startoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "!",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint/tokenizer_2/tokenizer_config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "!",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"49406": {
|
| 13 |
+
"content": "<|startoftext|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"49407": {
|
| 21 |
+
"content": "<|endoftext|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"bos_token": "<|startoftext|>",
|
| 30 |
+
"clean_up_tokenization_spaces": true,
|
| 31 |
+
"do_lower_case": true,
|
| 32 |
+
"eos_token": "<|endoftext|>",
|
| 33 |
+
"errors": "replace",
|
| 34 |
+
"model_max_length": 77,
|
| 35 |
+
"pad_token": "!",
|
| 36 |
+
"tokenizer_class": "CLIPTokenizer",
|
| 37 |
+
"unk_token": "<|endoftext|>"
|
| 38 |
+
}
|
checkpoint/tokenizer_2/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint/vae/config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "AutoencoderKL",
|
| 3 |
+
"_diffusers_version": "0.32.2",
|
| 4 |
+
"_name_or_path": "/data02/zhenchen/VTO_mobile/pretrained_models/stable-diffusion-3.5-large",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"block_out_channels": [
|
| 7 |
+
128,
|
| 8 |
+
256,
|
| 9 |
+
512,
|
| 10 |
+
512
|
| 11 |
+
],
|
| 12 |
+
"down_block_types": [
|
| 13 |
+
"DownEncoderBlock2D",
|
| 14 |
+
"DownEncoderBlock2D",
|
| 15 |
+
"DownEncoderBlock2D",
|
| 16 |
+
"DownEncoderBlock2D"
|
| 17 |
+
],
|
| 18 |
+
"force_upcast": true,
|
| 19 |
+
"in_channels": 3,
|
| 20 |
+
"latent_channels": 16,
|
| 21 |
+
"latents_mean": null,
|
| 22 |
+
"latents_std": null,
|
| 23 |
+
"layers_per_block": 2,
|
| 24 |
+
"mid_block_add_attention": true,
|
| 25 |
+
"norm_num_groups": 32,
|
| 26 |
+
"out_channels": 3,
|
| 27 |
+
"sample_size": 1024,
|
| 28 |
+
"scaling_factor": 1.5305,
|
| 29 |
+
"shift_factor": 0.0609,
|
| 30 |
+
"up_block_types": [
|
| 31 |
+
"UpDecoderBlock2D",
|
| 32 |
+
"UpDecoderBlock2D",
|
| 33 |
+
"UpDecoderBlock2D",
|
| 34 |
+
"UpDecoderBlock2D"
|
| 35 |
+
],
|
| 36 |
+
"use_post_quant_conv": false,
|
| 37 |
+
"use_quant_conv": false
|
| 38 |
+
}
|
checkpoint/vae/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:965f71f229a5981c0a025db771d8868998f5e4e8412dc5585c687f638fa59679
|
| 3 |
+
size 335306212
|
checkpoint/vae_decoder/decoder.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"in_channels": 16,
|
| 3 |
+
"out_channels": 3,
|
| 4 |
+
"up_block_types": [
|
| 5 |
+
"DecoderUpBlock2D",
|
| 6 |
+
"DecoderUpBlock2D",
|
| 7 |
+
"DecoderUpBlock2D",
|
| 8 |
+
"DecoderUpBlock2D"
|
| 9 |
+
],
|
| 10 |
+
"block_out_channels": [
|
| 11 |
+
64,
|
| 12 |
+
128,
|
| 13 |
+
256,
|
| 14 |
+
256
|
| 15 |
+
],
|
| 16 |
+
"layers_per_block": 2,
|
| 17 |
+
"norm_num_groups": 32,
|
| 18 |
+
"act_fn": "hardswish",
|
| 19 |
+
"mid_block_add_attention": false,
|
| 20 |
+
"conv_in_module": "Conv2d",
|
| 21 |
+
"conv_in_dw_bias": true,
|
| 22 |
+
"conv_in_pw_bias": false,
|
| 23 |
+
"conv_out_module": "Conv2d",
|
| 24 |
+
"conv_out_dw_bias": true,
|
| 25 |
+
"conv_out_pw_bias": false,
|
| 26 |
+
"use_mid_block": false,
|
| 27 |
+
"mid_block_type": "DecoderUNetMidBlock2D",
|
| 28 |
+
"mid_block_use_additional_resnet": true,
|
| 29 |
+
"resnet_middle_expansion": null,
|
| 30 |
+
"resnet_module": "DecoderResnetBlock2D",
|
| 31 |
+
"resnet_conv_module": "DecoderSepConv2d",
|
| 32 |
+
"attn_module": "Attention",
|
| 33 |
+
"attn_processor_type": "AttnProcessor2_0",
|
| 34 |
+
"kv_heads": 1,
|
| 35 |
+
"qk_norm": "layer_norm",
|
| 36 |
+
"layers_per_blocks": [
|
| 37 |
+
3,
|
| 38 |
+
3,
|
| 39 |
+
2,
|
| 40 |
+
1
|
| 41 |
+
],
|
| 42 |
+
"backward_output_channels": true,
|
| 43 |
+
"upsample_module": "Upsample2D",
|
| 44 |
+
"upsample_conv_module": "Conv2d",
|
| 45 |
+
"resnet_dw_bias": true,
|
| 46 |
+
"resnet_pw_bias": true
|
| 47 |
+
}
|
checkpoint/vae_decoder/decoder.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13ab9dec8e181b6d0e2efa3ecf466018b009bf5251c798f7aafc0b258106eb17
|
| 3 |
+
size 7644444
|