Hugging Face's logo

fancyfeast
/
big-asp-2

Diffusers
Safetensors
Model card Files
xet
Community
fancyfeast commited on
Commit
ccbc51f
·
verified ·
1 Parent(s): 268616a

Upload folder using huggingface_hub

Browse files
Files changed (42) hide show
  1. cuwm1gxo/samples_38133760/text_encoder/config.json +25 -0
  2. cuwm1gxo/samples_38133760/text_encoder/model.safetensors +3 -0
  3. cuwm1gxo/samples_38133760/unet/config.json +73 -0
  4. cuwm1gxo/samples_38133760/unet/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
  5. cuwm1gxo/samples_38133760/unet/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
  6. cuwm1gxo/samples_38133760/unet/diffusion_pytorch_model.safetensors.index.json +0 -0
  7. cuwm1gxo/samples_38635520/text_encoder/config.json +25 -0
  8. cuwm1gxo/samples_38635520/text_encoder/model.safetensors +3 -0
  9. cuwm1gxo/samples_38635520/unet/config.json +73 -0
  10. cuwm1gxo/samples_38635520/unet/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
  11. cuwm1gxo/samples_38635520/unet/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
  12. cuwm1gxo/samples_38635520/unet/diffusion_pytorch_model.safetensors.index.json +0 -0
  13. cuwm1gxo/samples_39137280/text_encoder/config.json +25 -0
  14. cuwm1gxo/samples_39137280/text_encoder/model.safetensors +3 -0
  15. cuwm1gxo/samples_39137280/training_state.pt +3 -0
  16. cuwm1gxo/samples_39137280/training_state0.pt +3 -0
  17. cuwm1gxo/samples_39137280/training_state1.pt +3 -0
  18. cuwm1gxo/samples_39137280/training_state2.pt +3 -0
  19. cuwm1gxo/samples_39137280/training_state3.pt +3 -0
  20. cuwm1gxo/samples_39137280/training_state4.pt +3 -0
  21. cuwm1gxo/samples_39137280/training_state5.pt +3 -0
  22. cuwm1gxo/samples_39137280/training_state6.pt +3 -0
  23. cuwm1gxo/samples_39137280/training_state7.pt +3 -0
  24. cuwm1gxo/samples_39137280/unet/config.json +73 -0
  25. cuwm1gxo/samples_39137280/unet/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
  26. cuwm1gxo/samples_39137280/unet/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
  27. cuwm1gxo/samples_39137280/unet/diffusion_pytorch_model.safetensors.index.json +0 -0
  28. cuwm1gxo/samples_39639040/text_encoder/config.json +25 -0
  29. cuwm1gxo/samples_39639040/text_encoder/model.safetensors +3 -0
  30. cuwm1gxo/samples_39639040/training_state.pt +3 -0
  31. cuwm1gxo/samples_39639040/training_state0.pt +3 -0
  32. cuwm1gxo/samples_39639040/training_state1.pt +3 -0
  33. cuwm1gxo/samples_39639040/training_state2.pt +3 -0
  34. cuwm1gxo/samples_39639040/training_state3.pt +3 -0
  35. cuwm1gxo/samples_39639040/training_state4.pt +3 -0
  36. cuwm1gxo/samples_39639040/training_state5.pt +3 -0
  37. cuwm1gxo/samples_39639040/training_state6.pt +3 -0
  38. cuwm1gxo/samples_39639040/training_state7.pt +3 -0
  39. cuwm1gxo/samples_39639040/unet/config.json +73 -0
  40. cuwm1gxo/samples_39639040/unet/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
  41. cuwm1gxo/samples_39639040/unet/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
  42. cuwm1gxo/samples_39639040/unet/diffusion_pytorch_model.safetensors.index.json +0 -0
cuwm1gxo/samples_38133760/text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
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": "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": "float32",
23
+ "transformers_version": "4.45.2",
24
+ "vocab_size": 49408
25
+ }
cuwm1gxo/samples_38133760/text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b25982d19683c034b09ec670f86655a201d5ef37e5edddd3195c6f6bf15b21b
3
+ size 492265168
cuwm1gxo/samples_38133760/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.30.3",
4
+ "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": "text_time",
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": 256,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20
13
+ ],
14
+ "attention_type": "default",
15
+ "block_out_channels": [
16
+ 320,
17
+ 640,
18
+ 1280
19
+ ],
20
+ "center_input_sample": false,
21
+ "class_embed_type": null,
22
+ "class_embeddings_concat": false,
23
+ "conv_in_kernel": 3,
24
+ "conv_out_kernel": 3,
25
+ "cross_attention_dim": 2048,
26
+ "cross_attention_norm": null,
27
+ "down_block_types": [
28
+ "DownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D"
31
+ ],
32
+ "downsample_padding": 1,
33
+ "dropout": 0.0,
34
+ "dual_cross_attention": false,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "in_channels": 4,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "norm_eps": 1e-05,
45
+ "norm_num_groups": 32,
46
+ "num_attention_heads": null,
47
+ "num_class_embeds": null,
48
+ "only_cross_attention": false,
49
+ "out_channels": 4,
50
+ "projection_class_embeddings_input_dim": 2816,
51
+ "resnet_out_scale_factor": 1.0,
52
+ "resnet_skip_time_act": false,
53
+ "resnet_time_scale_shift": "default",
54
+ "reverse_transformer_layers_per_block": null,
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": [
62
+ 1,
63
+ 2,
64
+ 10
65
+ ],
66
+ "up_block_types": [
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "UpBlock2D"
70
+ ],
71
+ "upcast_attention": null,
72
+ "use_linear_projection": true
73
+ }
cuwm1gxo/samples_38133760/unet/diffusion_pytorch_model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84f286086dc7335a9f304aedb6398a2157fc53797fbd30f1b2ea11d498e3bc46
3
+ size 9988139160
cuwm1gxo/samples_38133760/unet/diffusion_pytorch_model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5847e99c82cbde1018992d001bca90b67301be21b1f0210b0b3027eb33531765
3
+ size 281938304
cuwm1gxo/samples_38133760/unet/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
cuwm1gxo/samples_38635520/text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
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": "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": "float32",
23
+ "transformers_version": "4.45.2",
24
+ "vocab_size": 49408
25
+ }
cuwm1gxo/samples_38635520/text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:229936f251a1c5e6ccc2ea045fb6340a512f18b074f653349917b60040157d04
3
+ size 492265168
cuwm1gxo/samples_38635520/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.30.3",
4
+ "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": "text_time",
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": 256,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20
13
+ ],
14
+ "attention_type": "default",
15
+ "block_out_channels": [
16
+ 320,
17
+ 640,
18
+ 1280
19
+ ],
20
+ "center_input_sample": false,
21
+ "class_embed_type": null,
22
+ "class_embeddings_concat": false,
23
+ "conv_in_kernel": 3,
24
+ "conv_out_kernel": 3,
25
+ "cross_attention_dim": 2048,
26
+ "cross_attention_norm": null,
27
+ "down_block_types": [
28
+ "DownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D"
31
+ ],
32
+ "downsample_padding": 1,
33
+ "dropout": 0.0,
34
+ "dual_cross_attention": false,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "in_channels": 4,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "norm_eps": 1e-05,
45
+ "norm_num_groups": 32,
46
+ "num_attention_heads": null,
47
+ "num_class_embeds": null,
48
+ "only_cross_attention": false,
49
+ "out_channels": 4,
50
+ "projection_class_embeddings_input_dim": 2816,
51
+ "resnet_out_scale_factor": 1.0,
52
+ "resnet_skip_time_act": false,
53
+ "resnet_time_scale_shift": "default",
54
+ "reverse_transformer_layers_per_block": null,
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": [
62
+ 1,
63
+ 2,
64
+ 10
65
+ ],
66
+ "up_block_types": [
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "UpBlock2D"
70
+ ],
71
+ "upcast_attention": null,
72
+ "use_linear_projection": true
73
+ }
cuwm1gxo/samples_38635520/unet/diffusion_pytorch_model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89c3556b1ffe9da1bf139b01985defd6821078fae3a08f399eb1f28286688428
3
+ size 9988139160
cuwm1gxo/samples_38635520/unet/diffusion_pytorch_model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8df94cd6fe1469eac6dd8a825c6d6db26802d41c50472529b8f5b18cd8c07304
3
+ size 281938304
cuwm1gxo/samples_38635520/unet/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
cuwm1gxo/samples_39137280/text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
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": "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": "float32",
23
+ "transformers_version": "4.45.2",
24
+ "vocab_size": 49408
25
+ }
cuwm1gxo/samples_39137280/text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00bf9447543d85f790f63220c6015d50f9cd6a6eccccae63a93ce356041fe4a3
3
+ size 492265168
cuwm1gxo/samples_39137280/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62efe7acb9024a735e97cb9d035e0adf815449271a31700c147bff119c36634a
3
+ size 21469127066
cuwm1gxo/samples_39137280/training_state0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97654dd9c09439bf3ce08a09dd17d500e70adbe4b81e6e7a36c5339857378242
3
+ size 14536
cuwm1gxo/samples_39137280/training_state1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba90d4846fbb9150e607a2bd53fc9c8b3b0b53695ffa417a08914f13490fb007
3
+ size 14600
cuwm1gxo/samples_39137280/training_state2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d76e5ab2ea064411693724388a0c72b09d5f1a47d7ba0d5f438975add1b13c25
3
+ size 14536
cuwm1gxo/samples_39137280/training_state3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cb4a0295ad17a5953c4816c8c9057684c2d31cd31f72af9b00a7603989ccda1
3
+ size 14600
cuwm1gxo/samples_39137280/training_state4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:167b337c699217502f226add7b9ceca60b3e986ac6b48491f7611609cf015e4b
3
+ size 14536
cuwm1gxo/samples_39137280/training_state5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e1b6903ee064fb4f75dbfdcb8c2eb27171edd99c46a109bd494637c47971027
3
+ size 14472
cuwm1gxo/samples_39137280/training_state6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4147d63189ff8d4f6ba151f8c4438b8a3f938db512b4f31f758ceb0db6baf4d2
3
+ size 14600
cuwm1gxo/samples_39137280/training_state7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23ab64783c24f231ba6eaa496adc1aa08146e39d811c9c5dd67d13f4757cd3e0
3
+ size 14600
cuwm1gxo/samples_39137280/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.30.3",
4
+ "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": "text_time",
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": 256,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20
13
+ ],
14
+ "attention_type": "default",
15
+ "block_out_channels": [
16
+ 320,
17
+ 640,
18
+ 1280
19
+ ],
20
+ "center_input_sample": false,
21
+ "class_embed_type": null,
22
+ "class_embeddings_concat": false,
23
+ "conv_in_kernel": 3,
24
+ "conv_out_kernel": 3,
25
+ "cross_attention_dim": 2048,
26
+ "cross_attention_norm": null,
27
+ "down_block_types": [
28
+ "DownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D"
31
+ ],
32
+ "downsample_padding": 1,
33
+ "dropout": 0.0,
34
+ "dual_cross_attention": false,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "in_channels": 4,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "norm_eps": 1e-05,
45
+ "norm_num_groups": 32,
46
+ "num_attention_heads": null,
47
+ "num_class_embeds": null,
48
+ "only_cross_attention": false,
49
+ "out_channels": 4,
50
+ "projection_class_embeddings_input_dim": 2816,
51
+ "resnet_out_scale_factor": 1.0,
52
+ "resnet_skip_time_act": false,
53
+ "resnet_time_scale_shift": "default",
54
+ "reverse_transformer_layers_per_block": null,
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": [
62
+ 1,
63
+ 2,
64
+ 10
65
+ ],
66
+ "up_block_types": [
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "UpBlock2D"
70
+ ],
71
+ "upcast_attention": null,
72
+ "use_linear_projection": true
73
+ }
cuwm1gxo/samples_39137280/unet/diffusion_pytorch_model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dded7f25f170bfc459b2092c22cc2492c852df4ece367b40482183cf24259bd
3
+ size 9988139160
cuwm1gxo/samples_39137280/unet/diffusion_pytorch_model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7a6abfd51f121395cad411284bb8132ef96341d6ebcdbb15be881f94d8d60ef
3
+ size 281938304
cuwm1gxo/samples_39137280/unet/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
cuwm1gxo/samples_39639040/text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
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": "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": "float32",
23
+ "transformers_version": "4.45.2",
24
+ "vocab_size": 49408
25
+ }
cuwm1gxo/samples_39639040/text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f89fb6a948b232c569cd97fab5e05433fde978d403644c29997c3cfb3da51666
3
+ size 492265168
cuwm1gxo/samples_39639040/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dad5db189b58a1b4176627f1d6606152d5caba77d4976012a8d606737996d48a
3
+ size 21469127066
cuwm1gxo/samples_39639040/training_state0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebb3feb5a33a70995c8d5e4d166244db49e4326deb49779ab9462f8cd87120c0
3
+ size 14536
cuwm1gxo/samples_39639040/training_state1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6708616b397bb953efaf3bbb3d5212c3e194a072243b8afc707d1d61c43f9ba2
3
+ size 14600
cuwm1gxo/samples_39639040/training_state2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:642d020a32a22cb93385086473c98b697fa1cf1d08b19c959b35dd572daefab8
3
+ size 14536
cuwm1gxo/samples_39639040/training_state3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8490737684f44588fbfd28ed10a52bc76a9c373d504cd315456f58166551b8ae
3
+ size 14600
cuwm1gxo/samples_39639040/training_state4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27ab78cf22d2258e4b685d6ba39a377a6e60626781f68cd379d95d2c816110f7
3
+ size 14536
cuwm1gxo/samples_39639040/training_state5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90f56bb57eea50a013abd3c6cb9836da0ea4c3058018986ffce4e93742691e83
3
+ size 14472
cuwm1gxo/samples_39639040/training_state6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65e362c2cc89c44181e5c8798b64249450478d88f0433dc8032b8201c41d0cbe
3
+ size 14600
cuwm1gxo/samples_39639040/training_state7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f70e5b6a64a62d8ef3894b55e771ec36c07ef11915c50c69b0e48d11dc32afa
3
+ size 14600
cuwm1gxo/samples_39639040/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.30.3",
4
+ "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": "text_time",
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": 256,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20
13
+ ],
14
+ "attention_type": "default",
15
+ "block_out_channels": [
16
+ 320,
17
+ 640,
18
+ 1280
19
+ ],
20
+ "center_input_sample": false,
21
+ "class_embed_type": null,
22
+ "class_embeddings_concat": false,
23
+ "conv_in_kernel": 3,
24
+ "conv_out_kernel": 3,
25
+ "cross_attention_dim": 2048,
26
+ "cross_attention_norm": null,
27
+ "down_block_types": [
28
+ "DownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D"
31
+ ],
32
+ "downsample_padding": 1,
33
+ "dropout": 0.0,
34
+ "dual_cross_attention": false,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "in_channels": 4,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "norm_eps": 1e-05,
45
+ "norm_num_groups": 32,
46
+ "num_attention_heads": null,
47
+ "num_class_embeds": null,
48
+ "only_cross_attention": false,
49
+ "out_channels": 4,
50
+ "projection_class_embeddings_input_dim": 2816,
51
+ "resnet_out_scale_factor": 1.0,
52
+ "resnet_skip_time_act": false,
53
+ "resnet_time_scale_shift": "default",
54
+ "reverse_transformer_layers_per_block": null,
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": [
62
+ 1,
63
+ 2,
64
+ 10
65
+ ],
66
+ "up_block_types": [
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "UpBlock2D"
70
+ ],
71
+ "upcast_attention": null,
72
+ "use_linear_projection": true
73
+ }
cuwm1gxo/samples_39639040/unet/diffusion_pytorch_model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:364687116c5ad7b8fecbf184dda2e19b85562760c076eebda98e17e5d5bda71c
3
+ size 9988139160
cuwm1gxo/samples_39639040/unet/diffusion_pytorch_model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ab8cc916dacb0896f694ef75f3a2d3fda8200395ed448061fb7792f82ac7185
3
+ size 281938304
cuwm1gxo/samples_39639040/unet/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff