Hugging Face's logo

zwpro
/
Free-TryOn

Diffusers
Safetensors
Model card Files
xet
Community
zwpro commited on
Commit
9dd2679
·
1 Parent(s): a71cc8b

first commit

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. enhance_vae-dc/config.json +47 -0
  2. enhance_vae-dc/diffusion_pytorch_model.safetensors +3 -0
  3. enhance_vae-hd/config.json +47 -0
  4. enhance_vae-hd/diffusion_pytorch_model.safetensors +3 -0
  5. scheduler/scheduler_config.json +20 -0
  6. stage1/dresscode/garment_encoder/config.json +29 -0
  7. stage1/dresscode/garment_encoder/diffusion_pytorch_model.safetensors +3 -0
  8. stage1/dresscode/garment_unet/config.json +70 -0
  9. stage1/dresscode/garment_unet/diffusion_pytorch_model.safetensors +3 -0
  10. stage1/dresscode/human_unet/config.json +56 -0
  11. stage1/dresscode/human_unet/diffusion_pytorch_model.safetensors +3 -0
  12. stage1/dresscode/pose_encoder/config.json +13 -0
  13. stage1/dresscode/pose_encoder/diffusion_pytorch_model.safetensors +3 -0
  14. stage1/vitonhd-1024/garment_encoder/config.json +29 -0
  15. stage1/vitonhd-1024/garment_encoder/diffusion_pytorch_model.safetensors +3 -0
  16. stage1/vitonhd-1024/garment_unet/config.json +70 -0
  17. stage1/vitonhd-1024/garment_unet/diffusion_pytorch_model.safetensors +3 -0
  18. stage1/vitonhd-1024/human_unet/config.json +56 -0
  19. stage1/vitonhd-1024/human_unet/diffusion_pytorch_model.safetensors +3 -0
  20. stage1/vitonhd-1024/pose_encoder/config.json +13 -0
  21. stage1/vitonhd-1024/pose_encoder/diffusion_pytorch_model.safetensors +3 -0
  22. stage1/vitonhd/garment_encoder/config.json +29 -0
  23. stage1/vitonhd/garment_encoder/diffusion_pytorch_model.safetensors +3 -0
  24. stage1/vitonhd/garment_unet/config.json +70 -0
  25. stage1/vitonhd/garment_unet/diffusion_pytorch_model.safetensors +3 -0
  26. stage1/vitonhd/human_unet/config.json +56 -0
  27. stage1/vitonhd/human_unet/diffusion_pytorch_model.safetensors +3 -0
  28. stage1/vitonhd/pose_encoder/config.json +13 -0
  29. stage1/vitonhd/pose_encoder/diffusion_pytorch_model.safetensors +3 -0
  30. stage2/dresscode/garment_encoder/config.json +29 -0
  31. stage2/dresscode/garment_encoder/diffusion_pytorch_model.safetensors +3 -0
  32. stage2/dresscode/garment_unet/config.json +70 -0
  33. stage2/dresscode/garment_unet/diffusion_pytorch_model.safetensors +3 -0
  34. stage2/dresscode/human_unet/config.json +56 -0
  35. stage2/dresscode/human_unet/diffusion_pytorch_model.safetensors +3 -0
  36. stage2/vitonhd-1024/garment_encoder/config.json +29 -0
  37. stage2/vitonhd-1024/garment_encoder/diffusion_pytorch_model.safetensors +3 -0
  38. stage2/vitonhd-1024/garment_unet/config.json +70 -0
  39. stage2/vitonhd-1024/garment_unet/diffusion_pytorch_model.safetensors +3 -0
  40. stage2/vitonhd-1024/human_unet/config.json +56 -0
  41. stage2/vitonhd-1024/human_unet/diffusion_pytorch_model.safetensors +3 -0
  42. stage2/vitonhd/garment_encoder/config.json +29 -0
  43. stage2/vitonhd/garment_encoder/diffusion_pytorch_model.safetensors +3 -0
  44. stage2/vitonhd/garment_unet/config.json +70 -0
  45. stage2/vitonhd/garment_unet/diffusion_pytorch_model.safetensors +3 -0
  46. stage2/vitonhd/human_unet/config.json +56 -0
  47. stage2/vitonhd/human_unet/diffusion_pytorch_model.safetensors +3 -0
  48. text_encoder/config.json +25 -0
  49. text_encoder/model.safetensors +3 -0
  50. tokenizer/merges.txt +0 -0
enhance_vae-dc/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/enhance-vae-dc",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "cloth_in_list": [
13
+ 512,
14
+ 256,
15
+ 128
16
+ ],
17
+ "down_block_types": [
18
+ "DownEncoderBlock2D",
19
+ "DownEncoderBlock2D",
20
+ "DownEncoderBlock2D",
21
+ "DownEncoderBlock2D"
22
+ ],
23
+ "force_upcast": true,
24
+ "heads": [
25
+ 16,
26
+ 16,
27
+ 8
28
+ ],
29
+ "human_in_list": [
30
+ 512,
31
+ 256,
32
+ 128
33
+ ],
34
+ "in_channels": 3,
35
+ "latent_channels": 4,
36
+ "layers_per_block": 2,
37
+ "norm_num_groups": 32,
38
+ "out_channels": 3,
39
+ "sample_size": 512,
40
+ "scaling_factor": 0.18215,
41
+ "up_block_types": [
42
+ "UpDecoderBlock2D",
43
+ "UpDecoderBlock2D",
44
+ "UpDecoderBlock2D",
45
+ "UpDecoderBlock2D"
46
+ ]
47
+ }
enhance_vae-dc/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5306948742e4982b421a968a2b6b2b036ba9e0dcfe2aaa06ba869994b1e3727
3
+ size 475631044
enhance_vae-hd/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/enhance-vae-hd",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "cloth_in_list": [
13
+ 512,
14
+ 256,
15
+ 128
16
+ ],
17
+ "down_block_types": [
18
+ "DownEncoderBlock2D",
19
+ "DownEncoderBlock2D",
20
+ "DownEncoderBlock2D",
21
+ "DownEncoderBlock2D"
22
+ ],
23
+ "force_upcast": true,
24
+ "heads": [
25
+ 16,
26
+ 16,
27
+ 8
28
+ ],
29
+ "human_in_list": [
30
+ 512,
31
+ 256,
32
+ 128
33
+ ],
34
+ "in_channels": 3,
35
+ "latent_channels": 4,
36
+ "layers_per_block": 2,
37
+ "norm_num_groups": 32,
38
+ "out_channels": 3,
39
+ "sample_size": 512,
40
+ "scaling_factor": 0.18215,
41
+ "up_block_types": [
42
+ "UpDecoderBlock2D",
43
+ "UpDecoderBlock2D",
44
+ "UpDecoderBlock2D",
45
+ "UpDecoderBlock2D"
46
+ ]
47
+ }
enhance_vae-hd/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb10568d53ae3e9f38ce6407405c13874f83569f9cf3d1a24d8d047b78c73be3
3
+ size 475631044
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDIMScheduler",
3
+ "_diffusers_version": "0.26.3",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "clip_sample_range": 1.0,
9
+ "dynamic_thresholding_ratio": 0.995,
10
+ "num_train_timesteps": 1000,
11
+ "prediction_type": "epsilon",
12
+ "rescale_betas_zero_snr": false,
13
+ "sample_max_value": 1.0,
14
+ "set_alpha_to_one": false,
15
+ "skip_prk_steps": true,
16
+ "steps_offset": 1,
17
+ "thresholding": false,
18
+ "timestep_spacing": "leading",
19
+ "trained_betas": null
20
+ }
stage1/dresscode/garment_encoder/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "Garment_Encoder",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/stage1/dresscode/garment_encoder",
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
+ "in_channels": 3,
19
+ "layers_per_block": 2,
20
+ "norm_num_groups": 32,
21
+ "out_channels": 320,
22
+ "sample_size": 512,
23
+ "up_block_types": [
24
+ "UpDecoderBlock2D",
25
+ "UpDecoderBlock2D",
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D"
28
+ ]
29
+ }
stage1/dresscode/garment_encoder/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fee232cb5fbe00b9d663c5026e0ece9bc387c701e8ebb0781b07936882bc5c4a
3
+ size 100435464
stage1/dresscode/garment_unet/config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/stage1/dresscode/garment_unet",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "block_out_channels": [
16
+ 320,
17
+ 640,
18
+ 1280,
19
+ 1280
20
+ ],
21
+ "center_input_sample": false,
22
+ "class_embed_type": null,
23
+ "class_embeddings_concat": false,
24
+ "conv_in_kernel": 3,
25
+ "conv_out_kernel": 3,
26
+ "cross_attention_dim": 1024,
27
+ "cross_attention_norm": null,
28
+ "down_block_types": [
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "DownBlock2D"
33
+ ],
34
+ "downsample_padding": 1,
35
+ "dual_cross_attention": false,
36
+ "encoder_hid_dim": null,
37
+ "encoder_hid_dim_type": null,
38
+ "flip_sin_to_cos": true,
39
+ "freq_shift": 0,
40
+ "in_channels": 8,
41
+ "layers_per_block": 2,
42
+ "mid_block_only_cross_attention": null,
43
+ "mid_block_scale_factor": 1,
44
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
45
+ "norm_eps": 1e-05,
46
+ "norm_num_groups": 32,
47
+ "num_attention_heads": null,
48
+ "num_class_embeds": null,
49
+ "only_cross_attention": false,
50
+ "out_channels": 4,
51
+ "projection_class_embeddings_input_dim": null,
52
+ "resnet_out_scale_factor": 1.0,
53
+ "resnet_skip_time_act": false,
54
+ "resnet_time_scale_shift": "default",
55
+ "sample_size": 64,
56
+ "time_cond_proj_dim": null,
57
+ "time_embedding_act_fn": null,
58
+ "time_embedding_dim": null,
59
+ "time_embedding_type": "positional",
60
+ "timestep_post_act": null,
61
+ "transformer_layers_per_block": 1,
62
+ "up_block_types": [
63
+ "UpBlock2D",
64
+ "CrossAttnUpBlock2D",
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D"
67
+ ],
68
+ "upcast_attention": false,
69
+ "use_linear_projection": true
70
+ }
stage1/dresscode/garment_unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59b0af651984aafda81f17194bcb90dd6e31f185224cd0b0dd296c8941f4da0b
3
+ size 3463772592
stage1/dresscode/human_unet/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/stage1/dresscode/human_unet",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": [
7
+ 5,
8
+ 10,
9
+ 20,
10
+ 20
11
+ ],
12
+ "block_out_channels": [
13
+ 320,
14
+ 640,
15
+ 1280,
16
+ 1280
17
+ ],
18
+ "center_input_sample": false,
19
+ "class_embed_type": null,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 1024,
23
+ "down_block_types": [
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "DownBlock2D"
28
+ ],
29
+ "downsample_padding": 1,
30
+ "dual_cross_attention": false,
31
+ "flip_sin_to_cos": true,
32
+ "freq_shift": 0,
33
+ "in_channels": 9,
34
+ "layers_per_block": 2,
35
+ "mid_block_scale_factor": 1,
36
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
37
+ "norm_eps": 1e-05,
38
+ "norm_num_groups": 32,
39
+ "num_class_embeds": null,
40
+ "only_cross_attention": false,
41
+ "out_channels": 4,
42
+ "projection_class_embeddings_input_dim": null,
43
+ "resnet_time_scale_shift": "default",
44
+ "sample_size": 64,
45
+ "time_cond_proj_dim": null,
46
+ "time_embedding_type": "positional",
47
+ "timestep_post_act": null,
48
+ "up_block_types": [
49
+ "UpBlock2D",
50
+ "CrossAttnUpBlock2D",
51
+ "CrossAttnUpBlock2D",
52
+ "CrossAttnUpBlock2D"
53
+ ],
54
+ "upcast_attention": false,
55
+ "use_linear_projection": true
56
+ }
stage1/dresscode/human_unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e9a4dea1cd6f6e0ad5497d903abe971323f6388c5b228db3bab5d206996beeb
3
+ size 3463784120
stage1/dresscode/pose_encoder/config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetConditioningEmbedding",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/stage1/dresscode/pose_encoder",
5
+ "block_out_channels": [
6
+ 16,
7
+ 32,
8
+ 96,
9
+ 256
10
+ ],
11
+ "conditioning_channels": 3,
12
+ "conditioning_embedding_channels": 320
13
+ }
stage1/dresscode/pose_encoder/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d09ee3ac2e1da4593fce50f00da83033fe453612e765dd1cba89774a0fbca6b0
3
+ size 4347232
stage1/vitonhd-1024/garment_encoder/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "Garment_Encoder",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/stage1/vitonhd-1024/garment_encoder",
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
+ "in_channels": 3,
19
+ "layers_per_block": 2,
20
+ "norm_num_groups": 32,
21
+ "out_channels": 320,
22
+ "sample_size": 1024,
23
+ "up_block_types": [
24
+ "UpDecoderBlock2D",
25
+ "UpDecoderBlock2D",
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D"
28
+ ]
29
+ }
stage1/vitonhd-1024/garment_encoder/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:118cdd1b6ac375a213878c5d81cd02f0c16a1cf87995a719ebfe97f13d567eac
3
+ size 100435464
stage1/vitonhd-1024/garment_unet/config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/stage1/vitonhd-1024/garment_unet",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "block_out_channels": [
16
+ 320,
17
+ 640,
18
+ 1280,
19
+ 1280
20
+ ],
21
+ "center_input_sample": false,
22
+ "class_embed_type": null,
23
+ "class_embeddings_concat": false,
24
+ "conv_in_kernel": 3,
25
+ "conv_out_kernel": 3,
26
+ "cross_attention_dim": 1024,
27
+ "cross_attention_norm": null,
28
+ "down_block_types": [
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "DownBlock2D"
33
+ ],
34
+ "downsample_padding": 1,
35
+ "dual_cross_attention": false,
36
+ "encoder_hid_dim": null,
37
+ "encoder_hid_dim_type": null,
38
+ "flip_sin_to_cos": true,
39
+ "freq_shift": 0,
40
+ "in_channels": 8,
41
+ "layers_per_block": 2,
42
+ "mid_block_only_cross_attention": null,
43
+ "mid_block_scale_factor": 1,
44
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
45
+ "norm_eps": 1e-05,
46
+ "norm_num_groups": 32,
47
+ "num_attention_heads": null,
48
+ "num_class_embeds": null,
49
+ "only_cross_attention": false,
50
+ "out_channels": 4,
51
+ "projection_class_embeddings_input_dim": null,
52
+ "resnet_out_scale_factor": 1.0,
53
+ "resnet_skip_time_act": false,
54
+ "resnet_time_scale_shift": "default",
55
+ "sample_size": 128,
56
+ "time_cond_proj_dim": null,
57
+ "time_embedding_act_fn": null,
58
+ "time_embedding_dim": null,
59
+ "time_embedding_type": "positional",
60
+ "timestep_post_act": null,
61
+ "transformer_layers_per_block": 1,
62
+ "up_block_types": [
63
+ "UpBlock2D",
64
+ "CrossAttnUpBlock2D",
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D"
67
+ ],
68
+ "upcast_attention": false,
69
+ "use_linear_projection": true
70
+ }
stage1/vitonhd-1024/garment_unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4918f76408e8565463f098218d7b0c2f7378d24fffcdd7e07a7cb244c76a1dc
3
+ size 3463772592
stage1/vitonhd-1024/human_unet/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/stage1/vitonhd-1024/human_unet",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": [
7
+ 5,
8
+ 10,
9
+ 20,
10
+ 20
11
+ ],
12
+ "block_out_channels": [
13
+ 320,
14
+ 640,
15
+ 1280,
16
+ 1280
17
+ ],
18
+ "center_input_sample": false,
19
+ "class_embed_type": null,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 1024,
23
+ "down_block_types": [
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "DownBlock2D"
28
+ ],
29
+ "downsample_padding": 1,
30
+ "dual_cross_attention": false,
31
+ "flip_sin_to_cos": true,
32
+ "freq_shift": 0,
33
+ "in_channels": 9,
34
+ "layers_per_block": 2,
35
+ "mid_block_scale_factor": 1,
36
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
37
+ "norm_eps": 1e-05,
38
+ "norm_num_groups": 32,
39
+ "num_class_embeds": null,
40
+ "only_cross_attention": false,
41
+ "out_channels": 4,
42
+ "projection_class_embeddings_input_dim": null,
43
+ "resnet_time_scale_shift": "default",
44
+ "sample_size": 128,
45
+ "time_cond_proj_dim": null,
46
+ "time_embedding_type": "positional",
47
+ "timestep_post_act": null,
48
+ "up_block_types": [
49
+ "UpBlock2D",
50
+ "CrossAttnUpBlock2D",
51
+ "CrossAttnUpBlock2D",
52
+ "CrossAttnUpBlock2D"
53
+ ],
54
+ "upcast_attention": false,
55
+ "use_linear_projection": true
56
+ }
stage1/vitonhd-1024/human_unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fec51f2fcae9d61c8f875f6245b2581c8b01b0216b3062f055450bdff3cd259
3
+ size 3463784120
stage1/vitonhd-1024/pose_encoder/config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetConditioningEmbedding",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/stage1/vitonhd-1024/pose_encoder",
5
+ "block_out_channels": [
6
+ 16,
7
+ 32,
8
+ 96,
9
+ 256
10
+ ],
11
+ "conditioning_channels": 3,
12
+ "conditioning_embedding_channels": 320
13
+ }
stage1/vitonhd-1024/pose_encoder/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bff086ff8ac946d21968fffa77bd40930985e28db1948eb2960f202fc0bb9a9e
3
+ size 4347232
stage1/vitonhd/garment_encoder/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "Garment_Encoder",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/stage1/vitonhd/garment_encoder",
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
+ "in_channels": 3,
19
+ "layers_per_block": 2,
20
+ "norm_num_groups": 32,
21
+ "out_channels": 320,
22
+ "sample_size": 512,
23
+ "up_block_types": [
24
+ "UpDecoderBlock2D",
25
+ "UpDecoderBlock2D",
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D"
28
+ ]
29
+ }
stage1/vitonhd/garment_encoder/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:197d934cfd949947f397ac95eb2d00f073b1db5d3c88eb2bd599d19bd865c39c
3
+ size 100435464
stage1/vitonhd/garment_unet/config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/stage1/vitonhd/garment_unet",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "block_out_channels": [
16
+ 320,
17
+ 640,
18
+ 1280,
19
+ 1280
20
+ ],
21
+ "center_input_sample": false,
22
+ "class_embed_type": null,
23
+ "class_embeddings_concat": false,
24
+ "conv_in_kernel": 3,
25
+ "conv_out_kernel": 3,
26
+ "cross_attention_dim": 1024,
27
+ "cross_attention_norm": null,
28
+ "down_block_types": [
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "DownBlock2D"
33
+ ],
34
+ "downsample_padding": 1,
35
+ "dual_cross_attention": false,
36
+ "encoder_hid_dim": null,
37
+ "encoder_hid_dim_type": null,
38
+ "flip_sin_to_cos": true,
39
+ "freq_shift": 0,
40
+ "in_channels": 8,
41
+ "layers_per_block": 2,
42
+ "mid_block_only_cross_attention": null,
43
+ "mid_block_scale_factor": 1,
44
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
45
+ "norm_eps": 1e-05,
46
+ "norm_num_groups": 32,
47
+ "num_attention_heads": null,
48
+ "num_class_embeds": null,
49
+ "only_cross_attention": false,
50
+ "out_channels": 4,
51
+ "projection_class_embeddings_input_dim": null,
52
+ "resnet_out_scale_factor": 1.0,
53
+ "resnet_skip_time_act": false,
54
+ "resnet_time_scale_shift": "default",
55
+ "sample_size": 64,
56
+ "time_cond_proj_dim": null,
57
+ "time_embedding_act_fn": null,
58
+ "time_embedding_dim": null,
59
+ "time_embedding_type": "positional",
60
+ "timestep_post_act": null,
61
+ "transformer_layers_per_block": 1,
62
+ "up_block_types": [
63
+ "UpBlock2D",
64
+ "CrossAttnUpBlock2D",
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D"
67
+ ],
68
+ "upcast_attention": false,
69
+ "use_linear_projection": true
70
+ }
stage1/vitonhd/garment_unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c39abfbade5fb361936df29c0ea87157323afd6f029a0ade86ed7980fba5086
3
+ size 3463772592
stage1/vitonhd/human_unet/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/stage1/vitonhd/human_unet",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": [
7
+ 5,
8
+ 10,
9
+ 20,
10
+ 20
11
+ ],
12
+ "block_out_channels": [
13
+ 320,
14
+ 640,
15
+ 1280,
16
+ 1280
17
+ ],
18
+ "center_input_sample": false,
19
+ "class_embed_type": null,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 1024,
23
+ "down_block_types": [
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "DownBlock2D"
28
+ ],
29
+ "downsample_padding": 1,
30
+ "dual_cross_attention": false,
31
+ "flip_sin_to_cos": true,
32
+ "freq_shift": 0,
33
+ "in_channels": 9,
34
+ "layers_per_block": 2,
35
+ "mid_block_scale_factor": 1,
36
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
37
+ "norm_eps": 1e-05,
38
+ "norm_num_groups": 32,
39
+ "num_class_embeds": null,
40
+ "only_cross_attention": false,
41
+ "out_channels": 4,
42
+ "projection_class_embeddings_input_dim": null,
43
+ "resnet_time_scale_shift": "default",
44
+ "sample_size": 64,
45
+ "time_cond_proj_dim": null,
46
+ "time_embedding_type": "positional",
47
+ "timestep_post_act": null,
48
+ "up_block_types": [
49
+ "UpBlock2D",
50
+ "CrossAttnUpBlock2D",
51
+ "CrossAttnUpBlock2D",
52
+ "CrossAttnUpBlock2D"
53
+ ],
54
+ "upcast_attention": false,
55
+ "use_linear_projection": true
56
+ }
stage1/vitonhd/human_unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7d7c9a9940264ae02576a7ff9ef1f966d97d190507cb000d45a5f0431bbc05b
3
+ size 3463784120
stage1/vitonhd/pose_encoder/config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetConditioningEmbedding",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/stage1/vitonhd/pose_encoder",
5
+ "block_out_channels": [
6
+ 16,
7
+ 32,
8
+ 96,
9
+ 256
10
+ ],
11
+ "conditioning_channels": 3,
12
+ "conditioning_embedding_channels": 320
13
+ }
stage1/vitonhd/pose_encoder/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e60c5f61d14c6e4dcf794331e627bfcb1cd858b2ea584f708bcc74152a320ac
3
+ size 4347232
stage2/dresscode/garment_encoder/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "Garment_Encoder",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/stage2/dresscode/garment_encoder",
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
+ "in_channels": 3,
19
+ "layers_per_block": 2,
20
+ "norm_num_groups": 32,
21
+ "out_channels": 320,
22
+ "sample_size": 512,
23
+ "up_block_types": [
24
+ "UpDecoderBlock2D",
25
+ "UpDecoderBlock2D",
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D"
28
+ ]
29
+ }
stage2/dresscode/garment_encoder/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:523c9f78f9b8ab2ed4f9ccd7f780c4f0cd029c7ea1f5e1a32b4142da33115e78
3
+ size 100435464
stage2/dresscode/garment_unet/config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/stage2/dresscode/garment_unet",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "block_out_channels": [
16
+ 320,
17
+ 640,
18
+ 1280,
19
+ 1280
20
+ ],
21
+ "center_input_sample": false,
22
+ "class_embed_type": null,
23
+ "class_embeddings_concat": false,
24
+ "conv_in_kernel": 3,
25
+ "conv_out_kernel": 3,
26
+ "cross_attention_dim": 1024,
27
+ "cross_attention_norm": null,
28
+ "down_block_types": [
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "DownBlock2D"
33
+ ],
34
+ "downsample_padding": 1,
35
+ "dual_cross_attention": false,
36
+ "encoder_hid_dim": null,
37
+ "encoder_hid_dim_type": null,
38
+ "flip_sin_to_cos": true,
39
+ "freq_shift": 0,
40
+ "in_channels": 8,
41
+ "layers_per_block": 2,
42
+ "mid_block_only_cross_attention": null,
43
+ "mid_block_scale_factor": 1,
44
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
45
+ "norm_eps": 1e-05,
46
+ "norm_num_groups": 32,
47
+ "num_attention_heads": null,
48
+ "num_class_embeds": null,
49
+ "only_cross_attention": false,
50
+ "out_channels": 4,
51
+ "projection_class_embeddings_input_dim": null,
52
+ "resnet_out_scale_factor": 1.0,
53
+ "resnet_skip_time_act": false,
54
+ "resnet_time_scale_shift": "default",
55
+ "sample_size": 64,
56
+ "time_cond_proj_dim": null,
57
+ "time_embedding_act_fn": null,
58
+ "time_embedding_dim": null,
59
+ "time_embedding_type": "positional",
60
+ "timestep_post_act": null,
61
+ "transformer_layers_per_block": 1,
62
+ "up_block_types": [
63
+ "UpBlock2D",
64
+ "CrossAttnUpBlock2D",
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D"
67
+ ],
68
+ "upcast_attention": false,
69
+ "use_linear_projection": true
70
+ }
stage2/dresscode/garment_unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:894753c4156d4618913a26e73704e5d497f33bd0b18a652ea0a298fac9e163ec
3
+ size 3463772592
stage2/dresscode/human_unet/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/stage2/dresscode/human_unet",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": [
7
+ 5,
8
+ 10,
9
+ 20,
10
+ 20
11
+ ],
12
+ "block_out_channels": [
13
+ 320,
14
+ 640,
15
+ 1280,
16
+ 1280
17
+ ],
18
+ "center_input_sample": false,
19
+ "class_embed_type": null,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 1024,
23
+ "down_block_types": [
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "DownBlock2D"
28
+ ],
29
+ "downsample_padding": 1,
30
+ "dual_cross_attention": false,
31
+ "flip_sin_to_cos": true,
32
+ "freq_shift": 0,
33
+ "in_channels": 8,
34
+ "layers_per_block": 2,
35
+ "mid_block_scale_factor": 1,
36
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
37
+ "norm_eps": 1e-05,
38
+ "norm_num_groups": 32,
39
+ "num_class_embeds": null,
40
+ "only_cross_attention": false,
41
+ "out_channels": 4,
42
+ "projection_class_embeddings_input_dim": null,
43
+ "resnet_time_scale_shift": "default",
44
+ "sample_size": 64,
45
+ "time_cond_proj_dim": null,
46
+ "time_embedding_type": "positional",
47
+ "timestep_post_act": null,
48
+ "up_block_types": [
49
+ "UpBlock2D",
50
+ "CrossAttnUpBlock2D",
51
+ "CrossAttnUpBlock2D",
52
+ "CrossAttnUpBlock2D"
53
+ ],
54
+ "upcast_attention": false,
55
+ "use_linear_projection": true
56
+ }
stage2/dresscode/human_unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa5144cde4f3838270109bd55a4ab541948b64dc352558b9253056b36e5229a8
3
+ size 3463772592
stage2/vitonhd-1024/garment_encoder/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "Garment_Encoder",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/stage2/vitonhd-1024/garment_encoder",
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
+ "in_channels": 3,
19
+ "layers_per_block": 2,
20
+ "norm_num_groups": 32,
21
+ "out_channels": 320,
22
+ "sample_size": 1024,
23
+ "up_block_types": [
24
+ "UpDecoderBlock2D",
25
+ "UpDecoderBlock2D",
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D"
28
+ ]
29
+ }
stage2/vitonhd-1024/garment_encoder/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fa8f02691ccc4de764c5549dbb71ba80a6597f4e97427574fcebcb688c1534f
3
+ size 100435464
stage2/vitonhd-1024/garment_unet/config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/stage2/vitonhd-1024/garment_unet",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "block_out_channels": [
16
+ 320,
17
+ 640,
18
+ 1280,
19
+ 1280
20
+ ],
21
+ "center_input_sample": false,
22
+ "class_embed_type": null,
23
+ "class_embeddings_concat": false,
24
+ "conv_in_kernel": 3,
25
+ "conv_out_kernel": 3,
26
+ "cross_attention_dim": 1024,
27
+ "cross_attention_norm": null,
28
+ "down_block_types": [
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "DownBlock2D"
33
+ ],
34
+ "downsample_padding": 1,
35
+ "dual_cross_attention": false,
36
+ "encoder_hid_dim": null,
37
+ "encoder_hid_dim_type": null,
38
+ "flip_sin_to_cos": true,
39
+ "freq_shift": 0,
40
+ "in_channels": 8,
41
+ "layers_per_block": 2,
42
+ "mid_block_only_cross_attention": null,
43
+ "mid_block_scale_factor": 1,
44
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
45
+ "norm_eps": 1e-05,
46
+ "norm_num_groups": 32,
47
+ "num_attention_heads": null,
48
+ "num_class_embeds": null,
49
+ "only_cross_attention": false,
50
+ "out_channels": 4,
51
+ "projection_class_embeddings_input_dim": null,
52
+ "resnet_out_scale_factor": 1.0,
53
+ "resnet_skip_time_act": false,
54
+ "resnet_time_scale_shift": "default",
55
+ "sample_size": 128,
56
+ "time_cond_proj_dim": null,
57
+ "time_embedding_act_fn": null,
58
+ "time_embedding_dim": null,
59
+ "time_embedding_type": "positional",
60
+ "timestep_post_act": null,
61
+ "transformer_layers_per_block": 1,
62
+ "up_block_types": [
63
+ "UpBlock2D",
64
+ "CrossAttnUpBlock2D",
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D"
67
+ ],
68
+ "upcast_attention": false,
69
+ "use_linear_projection": true
70
+ }
stage2/vitonhd-1024/garment_unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f6ec1ec630d94cd2e8b55150f913ab29d4c63f4c92360341830eed1385d5868
3
+ size 3463772592
stage2/vitonhd-1024/human_unet/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/stage2/vitonhd-1024/human_unet",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": [
7
+ 5,
8
+ 10,
9
+ 20,
10
+ 20
11
+ ],
12
+ "block_out_channels": [
13
+ 320,
14
+ 640,
15
+ 1280,
16
+ 1280
17
+ ],
18
+ "center_input_sample": false,
19
+ "class_embed_type": null,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 1024,
23
+ "down_block_types": [
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "DownBlock2D"
28
+ ],
29
+ "downsample_padding": 1,
30
+ "dual_cross_attention": false,
31
+ "flip_sin_to_cos": true,
32
+ "freq_shift": 0,
33
+ "in_channels": 8,
34
+ "layers_per_block": 2,
35
+ "mid_block_scale_factor": 1,
36
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
37
+ "norm_eps": 1e-05,
38
+ "norm_num_groups": 32,
39
+ "num_class_embeds": null,
40
+ "only_cross_attention": false,
41
+ "out_channels": 4,
42
+ "projection_class_embeddings_input_dim": null,
43
+ "resnet_time_scale_shift": "default",
44
+ "sample_size": 128,
45
+ "time_cond_proj_dim": null,
46
+ "time_embedding_type": "positional",
47
+ "timestep_post_act": null,
48
+ "up_block_types": [
49
+ "UpBlock2D",
50
+ "CrossAttnUpBlock2D",
51
+ "CrossAttnUpBlock2D",
52
+ "CrossAttnUpBlock2D"
53
+ ],
54
+ "upcast_attention": false,
55
+ "use_linear_projection": true
56
+ }
stage2/vitonhd-1024/human_unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea135ec59594d815567525fa5397c61e2f5aebf244d27adf31e5a0b2093f6dc2
3
+ size 3463772592
stage2/vitonhd/garment_encoder/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "Garment_Encoder",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/stage2/vitonhd/garment_encoder",
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
+ "in_channels": 3,
19
+ "layers_per_block": 2,
20
+ "norm_num_groups": 32,
21
+ "out_channels": 320,
22
+ "sample_size": 512,
23
+ "up_block_types": [
24
+ "UpDecoderBlock2D",
25
+ "UpDecoderBlock2D",
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D"
28
+ ]
29
+ }
stage2/vitonhd/garment_encoder/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0788cc2cb45e8ad20c3867a885c6788fdf84ba5bc31ed3ca1a16d6e0416facb
3
+ size 100435464
stage2/vitonhd/garment_unet/config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/stage2/vitonhd/garment_unet",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "block_out_channels": [
16
+ 320,
17
+ 640,
18
+ 1280,
19
+ 1280
20
+ ],
21
+ "center_input_sample": false,
22
+ "class_embed_type": null,
23
+ "class_embeddings_concat": false,
24
+ "conv_in_kernel": 3,
25
+ "conv_out_kernel": 3,
26
+ "cross_attention_dim": 1024,
27
+ "cross_attention_norm": null,
28
+ "down_block_types": [
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "DownBlock2D"
33
+ ],
34
+ "downsample_padding": 1,
35
+ "dual_cross_attention": false,
36
+ "encoder_hid_dim": null,
37
+ "encoder_hid_dim_type": null,
38
+ "flip_sin_to_cos": true,
39
+ "freq_shift": 0,
40
+ "in_channels": 8,
41
+ "layers_per_block": 2,
42
+ "mid_block_only_cross_attention": null,
43
+ "mid_block_scale_factor": 1,
44
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
45
+ "norm_eps": 1e-05,
46
+ "norm_num_groups": 32,
47
+ "num_attention_heads": null,
48
+ "num_class_embeds": null,
49
+ "only_cross_attention": false,
50
+ "out_channels": 4,
51
+ "projection_class_embeddings_input_dim": null,
52
+ "resnet_out_scale_factor": 1.0,
53
+ "resnet_skip_time_act": false,
54
+ "resnet_time_scale_shift": "default",
55
+ "sample_size": 64,
56
+ "time_cond_proj_dim": null,
57
+ "time_embedding_act_fn": null,
58
+ "time_embedding_dim": null,
59
+ "time_embedding_type": "positional",
60
+ "timestep_post_act": null,
61
+ "transformer_layers_per_block": 1,
62
+ "up_block_types": [
63
+ "UpBlock2D",
64
+ "CrossAttnUpBlock2D",
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D"
67
+ ],
68
+ "upcast_attention": false,
69
+ "use_linear_projection": true
70
+ }
stage2/vitonhd/garment_unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6af5760db401203099cd4af05137b9b84f5f5fb9ca96bedb232dfc4a44b41fb9
3
+ size 3463772592
stage2/vitonhd/human_unet/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/stage2/vitonhd/human_unet",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": [
7
+ 5,
8
+ 10,
9
+ 20,
10
+ 20
11
+ ],
12
+ "block_out_channels": [
13
+ 320,
14
+ 640,
15
+ 1280,
16
+ 1280
17
+ ],
18
+ "center_input_sample": false,
19
+ "class_embed_type": null,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 1024,
23
+ "down_block_types": [
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "DownBlock2D"
28
+ ],
29
+ "downsample_padding": 1,
30
+ "dual_cross_attention": false,
31
+ "flip_sin_to_cos": true,
32
+ "freq_shift": 0,
33
+ "in_channels": 8,
34
+ "layers_per_block": 2,
35
+ "mid_block_scale_factor": 1,
36
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
37
+ "norm_eps": 1e-05,
38
+ "norm_num_groups": 32,
39
+ "num_class_embeds": null,
40
+ "only_cross_attention": false,
41
+ "out_channels": 4,
42
+ "projection_class_embeddings_input_dim": null,
43
+ "resnet_time_scale_shift": "default",
44
+ "sample_size": 64,
45
+ "time_cond_proj_dim": null,
46
+ "time_embedding_type": "positional",
47
+ "timestep_post_act": null,
48
+ "up_block_types": [
49
+ "UpBlock2D",
50
+ "CrossAttnUpBlock2D",
51
+ "CrossAttnUpBlock2D",
52
+ "CrossAttnUpBlock2D"
53
+ ],
54
+ "upcast_attention": false,
55
+ "use_linear_projection": true
56
+ }
stage2/vitonhd/human_unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1f5786d922d8895bf676ae1283799aed591ca34e7e97eaef68be09bff71fe66
3
+ size 3463772592
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/Free-tryon/test_checkpoint/text_encoder",
3
+ "architectures": [
4
+ "CLIPTextModel"
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": 1024,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 23,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 512,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.39.3",
24
+ "vocab_size": 49408
25
+ }
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67e013543d4fac905c882e2993d86a2d454ee69dc9e8f37c0c23d33a48959d15
3
+ size 1361596304
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff