Hugging Face's logo

fancyfeast
/
sdxl-bigasp-1

Diffusers
Safetensors
Model card Files
xet
Community
fancyfeast commited on
Commit
1d7fdbb
·
verified ·
1 Parent(s): 9266add

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. qu5qy3mq/samples_0/text_encoder/config.json +25 -0
  2. qu5qy3mq/samples_0/text_encoder/model.safetensors +3 -0
  3. qu5qy3mq/samples_0/training_state.pt +3 -0
  4. qu5qy3mq/samples_0/training_state0.pt +3 -0
  5. qu5qy3mq/samples_0/training_state1.pt +3 -0
  6. qu5qy3mq/samples_0/training_state2.pt +3 -0
  7. qu5qy3mq/samples_0/training_state3.pt +3 -0
  8. qu5qy3mq/samples_0/training_state4.pt +3 -0
  9. qu5qy3mq/samples_0/training_state5.pt +3 -0
  10. qu5qy3mq/samples_0/training_state6.pt +3 -0
  11. qu5qy3mq/samples_0/training_state7.pt +3 -0
  12. qu5qy3mq/samples_0/unet/config.json +73 -0
  13. qu5qy3mq/samples_0/unet/diffusion_pytorch_model.safetensors +3 -0
  14. qu5qy3mq/samples_1003520/text_encoder/config.json +25 -0
  15. qu5qy3mq/samples_1003520/text_encoder/model.safetensors +3 -0
  16. qu5qy3mq/samples_1003520/training_state.pt +3 -0
  17. qu5qy3mq/samples_1003520/training_state0.pt +3 -0
  18. qu5qy3mq/samples_1003520/training_state1.pt +3 -0
  19. qu5qy3mq/samples_1003520/training_state2.pt +3 -0
  20. qu5qy3mq/samples_1003520/training_state3.pt +3 -0
  21. qu5qy3mq/samples_1003520/training_state4.pt +3 -0
  22. qu5qy3mq/samples_1003520/training_state5.pt +3 -0
  23. qu5qy3mq/samples_1003520/training_state6.pt +3 -0
  24. qu5qy3mq/samples_1003520/training_state7.pt +3 -0
  25. qu5qy3mq/samples_1003520/unet/config.json +73 -0
  26. qu5qy3mq/samples_1003520/unet/diffusion_pytorch_model.safetensors +3 -0
  27. qu5qy3mq/samples_10035200/text_encoder/config.json +25 -0
  28. qu5qy3mq/samples_10035200/text_encoder/model.safetensors +3 -0
  29. qu5qy3mq/samples_10035200/training_state.pt +3 -0
  30. qu5qy3mq/samples_10035200/training_state0.pt +3 -0
  31. qu5qy3mq/samples_10035200/training_state1.pt +3 -0
  32. qu5qy3mq/samples_10035200/training_state2.pt +3 -0
  33. qu5qy3mq/samples_10035200/training_state3.pt +3 -0
  34. qu5qy3mq/samples_10035200/training_state4.pt +3 -0
  35. qu5qy3mq/samples_10035200/training_state5.pt +3 -0
  36. qu5qy3mq/samples_10035200/training_state6.pt +3 -0
  37. qu5qy3mq/samples_10035200/training_state7.pt +3 -0
  38. qu5qy3mq/samples_10035200/unet/config.json +73 -0
  39. qu5qy3mq/samples_10035200/unet/diffusion_pytorch_model.safetensors +3 -0
  40. qu5qy3mq/samples_11038720/text_encoder/config.json +25 -0
  41. qu5qy3mq/samples_11038720/text_encoder/model.safetensors +3 -0
  42. qu5qy3mq/samples_11038720/training_state.pt +3 -0
  43. qu5qy3mq/samples_11038720/training_state0.pt +3 -0
  44. qu5qy3mq/samples_11038720/training_state1.pt +3 -0
  45. qu5qy3mq/samples_11038720/training_state2.pt +3 -0
  46. qu5qy3mq/samples_11038720/training_state3.pt +3 -0
  47. qu5qy3mq/samples_11038720/training_state4.pt +3 -0
  48. qu5qy3mq/samples_11038720/training_state5.pt +3 -0
  49. qu5qy3mq/samples_11038720/training_state6.pt +3 -0
  50. qu5qy3mq/samples_11038720/training_state7.pt +3 -0
qu5qy3mq/samples_0/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": "4.41.2",
24
+ "vocab_size": 49408
25
+ }
qu5qy3mq/samples_0/text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c3d6454dd2d23414b56aa1b5858a72487a656937847b6fea8d0606d7a42cdbc
3
+ size 492265168
qu5qy3mq/samples_0/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2cf016c4ad028dd1bd5801bc8aa374e9df1409ffefbca7785a21cade90fbf90
3
+ size 6844
qu5qy3mq/samples_0/training_state0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a2d031542af73605f1193bdcebaf90a056f1741b17a6adbcd51acae06288c86
3
+ size 14536
qu5qy3mq/samples_0/training_state1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d6f36e61ce28d65aabd1d2c5227b88cb3b2e24a32e4aa722aad943f9101fd99
3
+ size 14600
qu5qy3mq/samples_0/training_state2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:657e1b352893f39d2881d67870a31a621034ed57c2ad0ac097e2df7410eac5aa
3
+ size 14536
qu5qy3mq/samples_0/training_state3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06476140ae637e2873ab3984bff387173820fb091390d0ad9cc93440b95ffd02
3
+ size 14600
qu5qy3mq/samples_0/training_state4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee4511ac12a07ba9d0f45eb5947b86912f4484ad9a40e02b78581d848e8dddb3
3
+ size 14536
qu5qy3mq/samples_0/training_state5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b002c4a01cf80ac6e2cf9f6da9bdf41098f5b44eb92d56187f76d3ae8a4683ce
3
+ size 14472
qu5qy3mq/samples_0/training_state6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d5c2d553d9283298a0585cd74ce46f263e229a463c46ddc4c61d967acc30ab4
3
+ size 14600
qu5qy3mq/samples_0/training_state7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b6aab945545bb0d5eab8f9e209c93462541421cc15f70d47094009591d3e700
3
+ size 14600
qu5qy3mq/samples_0/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.28.0",
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
+ }
qu5qy3mq/samples_0/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:357650fbfb3c7b4d94c1f5fd7664da819ad1ff5a839430484b4ec422d03f710a
3
+ size 10270077736
qu5qy3mq/samples_1003520/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": "4.41.2",
24
+ "vocab_size": 49408
25
+ }
qu5qy3mq/samples_1003520/text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c08926da8c30f8685a2b299593f1bc08d377cb87da08b3d54c3d9cd5120a1b6
3
+ size 492265168
qu5qy3mq/samples_1003520/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbd4f30d78a0bd68e4fd76dba5319c44560ff21c386811e9bb975d4456d2d622
3
+ size 21469127066
qu5qy3mq/samples_1003520/training_state0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2131c0aafc39f87fb5718b538bc7026738db68c5b68d9262c9c1d0e3484b58d5
3
+ size 14536
qu5qy3mq/samples_1003520/training_state1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52c9ae432fd2ab7a0edf3fb9a1790bd8449409975de0d01fb6ed340c70cfcb6f
3
+ size 14600
qu5qy3mq/samples_1003520/training_state2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:156a647c5dd4a7f711b989d3c53b1c5dd1e5cd71fc100cd3277ea252b963b253
3
+ size 14536
qu5qy3mq/samples_1003520/training_state3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aa7def66f2ea6979fb453df63b5848bc5c3a0951cf7757eb4ea894754e2026c
3
+ size 14600
qu5qy3mq/samples_1003520/training_state4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7505254c5390ba1369c7e4354c36bf7d6abdaa248fc9a05ef081ec9af38cbd4
3
+ size 14536
qu5qy3mq/samples_1003520/training_state5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a4a34d8adc4b355a3f80ded2ddf81b6e0c15e3e8c0ce2328df74737b5cdfd7c
3
+ size 14472
qu5qy3mq/samples_1003520/training_state6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50da7894ea06864d8e1b92949ab78a861eabc7e056429b06d21ef11b4b51b3b9
3
+ size 14600
qu5qy3mq/samples_1003520/training_state7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e387ccedab37cf24bfc1cfd94266579a9f728ee654c8a17fd428bda83d8819a6
3
+ size 14600
qu5qy3mq/samples_1003520/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.28.0",
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
+ }
qu5qy3mq/samples_1003520/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:392bccaaa442faa4a8d017902e4fec91ab485dc226b56643d32e48ca136cc58b
3
+ size 10270077736
qu5qy3mq/samples_10035200/text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "checkpoints/qu5qy3mq/samples_6522880",
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": "4.41.2",
24
+ "vocab_size": 49408
25
+ }
qu5qy3mq/samples_10035200/text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19f1fd4b0a7b401fda3455509fb1e86542e0b74595edaa580302030cd26522ba
3
+ size 492265168
qu5qy3mq/samples_10035200/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7a0cb2c2dbaa6b0af9560b31a078f7a6658b6d87651a565d62a583e7f8268e6
3
+ size 21469127066
qu5qy3mq/samples_10035200/training_state0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2159c3443f022dca0e5195d1b3a8333cc5ca629dc82adff656714e1de7f58e20
3
+ size 14536
qu5qy3mq/samples_10035200/training_state1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f42aa068b87a764e0fae0b42ad174b5d96ca230632924318b404233389fb4f75
3
+ size 14600
qu5qy3mq/samples_10035200/training_state2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:586dd79cbf47a31522b0039aebbbc8344b0523f444ffc690d3f71688379d3fc4
3
+ size 14536
qu5qy3mq/samples_10035200/training_state3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f36bafc424647210466339cf233bce9d97a5ef41d3e7bc333451b1e6ea75a8fb
3
+ size 14600
qu5qy3mq/samples_10035200/training_state4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d6f1c3ac2ee24c176e2c2c5107964bb0de75ca956b4e597a5c35d8a70931119
3
+ size 14536
qu5qy3mq/samples_10035200/training_state5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f382cc47dfe01d183434befb09bf7ec981a0b3dfb363d54ef70df3db84a94d22
3
+ size 14472
qu5qy3mq/samples_10035200/training_state6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b0b57e915a23e9b560ac7312590cd81e22024a42f7feeb275492ee29d7fbdb5
3
+ size 14600
qu5qy3mq/samples_10035200/training_state7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16cd8152e4f78d04e0879f50d93befaf4bb6798755f51edaa36125bc5d48e03c
3
+ size 14600
qu5qy3mq/samples_10035200/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.28.0",
4
+ "_name_or_path": "checkpoints/qu5qy3mq/samples_6522880",
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
+ }
qu5qy3mq/samples_10035200/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c987a327bd9f48cf764e480698a7dba46cb172fa8c860e5f1dfff82d839566b5
3
+ size 10270077736
qu5qy3mq/samples_11038720/text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "checkpoints/qu5qy3mq/samples_6522880",
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": "4.41.2",
24
+ "vocab_size": 49408
25
+ }
qu5qy3mq/samples_11038720/text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46988d744e230c50ab81d55eda6cfb75820d73e8b8cc5291632ae39ca90e66c3
3
+ size 492265168
qu5qy3mq/samples_11038720/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:725d713694ab1d102c89ea05a1eb9fa65b00487045266f06df1e93a87b103dc0
3
+ size 21469127066
qu5qy3mq/samples_11038720/training_state0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e212181f42805ab1f78ed996c00cd6fd1d5fc04cd82d1d9e2ff2f756e464c5d
3
+ size 14536
qu5qy3mq/samples_11038720/training_state1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40469e1ab7fa33e01fc1ee2da85d0df6f6ca405b12701a7e9a82198a109f3eac
3
+ size 14600
qu5qy3mq/samples_11038720/training_state2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:879df0ceee3dbb4f968085fc7fb384c342e77d1888c266b0ae4ba16efbfe1bac
3
+ size 14536
qu5qy3mq/samples_11038720/training_state3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2163b1109b72267479d999f54f8705c1a576f75b0fc32b33324a59f0f31f025
3
+ size 14600
qu5qy3mq/samples_11038720/training_state4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8705126fc62c39bd43e2b71ec009861874d4e5bdb6177047150e926a669e7f58
3
+ size 14536
qu5qy3mq/samples_11038720/training_state5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aa71a5a100a846ec6658495265a5b3bf39aa0daa3559f9616fa01ebfd57211d
3
+ size 14472
qu5qy3mq/samples_11038720/training_state6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b78acb6af3fb0d26e06ff02c74a614fc2fcabcb15cdaa5003e57b33748e3e474
3
+ size 14600
qu5qy3mq/samples_11038720/training_state7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fff8893c061874923bba6f62b1da2778c1b7fd24aad30a7d1c90508c708e211f
3
+ size 14600