Hugging Face's logo

juliajoanna
/
sd2-1-flintstones-model

Text-to-Image
Diffusers
TensorBoard
Safetensors
StableDiffusionPipeline
stable-diffusion
stable-diffusion-diffusers
Inference Endpoints
Model card Files Metrics Community
juliajoanna commited on
Commit
39590cc
•
1 Parent(s): 2924c08

End of training

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +46 -0
  2. checkpoint-1000/optimizer.bin +3 -0
  3. checkpoint-1000/random_states_0.pkl +3 -0
  4. checkpoint-1000/scheduler.bin +3 -0
  5. checkpoint-1000/unet/config.json +73 -0
  6. checkpoint-1000/unet/diffusion_pytorch_model.safetensors +3 -0
  7. checkpoint-1000/unet_ema/config.json +80 -0
  8. checkpoint-1000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  9. checkpoint-10000/optimizer.bin +3 -0
  10. checkpoint-10000/random_states_0.pkl +3 -0
  11. checkpoint-10000/scheduler.bin +3 -0
  12. checkpoint-10000/unet/config.json +73 -0
  13. checkpoint-10000/unet/diffusion_pytorch_model.safetensors +3 -0
  14. checkpoint-10000/unet_ema/config.json +80 -0
  15. checkpoint-10000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  16. checkpoint-10500/optimizer.bin +3 -0
  17. checkpoint-10500/random_states_0.pkl +3 -0
  18. checkpoint-10500/scheduler.bin +3 -0
  19. checkpoint-10500/unet/config.json +73 -0
  20. checkpoint-10500/unet/diffusion_pytorch_model.safetensors +3 -0
  21. checkpoint-10500/unet_ema/config.json +80 -0
  22. checkpoint-10500/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  23. checkpoint-11000/optimizer.bin +3 -0
  24. checkpoint-11000/random_states_0.pkl +3 -0
  25. checkpoint-11000/scheduler.bin +3 -0
  26. checkpoint-11000/unet/config.json +73 -0
  27. checkpoint-11000/unet/diffusion_pytorch_model.safetensors +3 -0
  28. checkpoint-11000/unet_ema/config.json +80 -0
  29. checkpoint-11000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  30. checkpoint-11500/optimizer.bin +3 -0
  31. checkpoint-11500/random_states_0.pkl +3 -0
  32. checkpoint-11500/scheduler.bin +3 -0
  33. checkpoint-11500/unet/config.json +73 -0
  34. checkpoint-11500/unet/diffusion_pytorch_model.safetensors +3 -0
  35. checkpoint-11500/unet_ema/config.json +80 -0
  36. checkpoint-11500/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  37. checkpoint-12000/optimizer.bin +3 -0
  38. checkpoint-12000/random_states_0.pkl +3 -0
  39. checkpoint-12000/scheduler.bin +3 -0
  40. checkpoint-12000/unet/config.json +73 -0
  41. checkpoint-12000/unet/diffusion_pytorch_model.safetensors +3 -0
  42. checkpoint-12000/unet_ema/config.json +80 -0
  43. checkpoint-12000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  44. checkpoint-12500/optimizer.bin +3 -0
  45. checkpoint-12500/random_states_0.pkl +3 -0
  46. checkpoint-12500/scheduler.bin +3 -0
  47. checkpoint-12500/unet/config.json +73 -0
  48. checkpoint-12500/unet/diffusion_pytorch_model.safetensors +3 -0
  49. checkpoint-12500/unet_ema/config.json +80 -0
  50. checkpoint-12500/unet_ema/diffusion_pytorch_model.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: creativeml-openrail-m
4
+ base_model: stabilityai/stable-diffusion-2-1
5
+ datasets:
6
+ - None
7
+ tags:
8
+ - stable-diffusion
9
+ - stable-diffusion-diffusers
10
+ - text-to-image
11
+ - diffusers
12
+ inference: true
13
+ ---
14
+
15
+ # Text-to-image finetuning - juliajoanna/sd2-1-flintstones-model
16
+
17
+ This pipeline was finetuned from **stabilityai/stable-diffusion-2-1** on the **None** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['Fred is driving a car']:
18
+
19
+ ![val_imgs_grid](./val_imgs_grid.png)
20
+
21
+
22
+ ## Pipeline usage
23
+
24
+ You can use the pipeline like so:
25
+
26
+ ```python
27
+ from diffusers import DiffusionPipeline
28
+ import torch
29
+
30
+ pipeline = DiffusionPipeline.from_pretrained("juliajoanna/sd2-1-flintstones-model", torch_dtype=torch.float16)
31
+ prompt = "Fred is driving a car"
32
+ image = pipeline(prompt).images[0]
33
+ image.save("my_image.png")
34
+ ```
35
+
36
+ ## Training info
37
+
38
+ These are the key hyperparameters used during training:
39
+
40
+ * Epochs: 0
41
+ * Learning rate: 1e-05
42
+ * Batch size: 1
43
+ * Gradient accumulation steps: 4
44
+ * Image resolution: 512
45
+ * Mixed-precision: None
46
+
checkpoint-1000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1d0e7f02d69b775ca0871f611f9198fd5f700e955d5e32e5e4e83158a148aba
3
+ size 6927867604
checkpoint-1000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96ebd386162b6003ba21675fa073eaa24eac494efeb90437a9f9a0984a0e1e4b
3
+ size 14344
checkpoint-1000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d16ae9dedf4c45ceadc467593037d83423677715e75ab402a9f44aa81de9b84
3
+ size 1000
checkpoint-1000/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
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
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "DownBlock2D"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "flip_sin_to_cos": true,
41
+ "freq_shift": 0,
42
+ "in_channels": 4,
43
+ "layers_per_block": 2,
44
+ "mid_block_only_cross_attention": null,
45
+ "mid_block_scale_factor": 1,
46
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
47
+ "norm_eps": 1e-05,
48
+ "norm_num_groups": 32,
49
+ "num_attention_heads": null,
50
+ "num_class_embeds": null,
51
+ "only_cross_attention": false,
52
+ "out_channels": 4,
53
+ "projection_class_embeddings_input_dim": null,
54
+ "resnet_out_scale_factor": 1.0,
55
+ "resnet_skip_time_act": false,
56
+ "resnet_time_scale_shift": "default",
57
+ "reverse_transformer_layers_per_block": null,
58
+ "sample_size": 64,
59
+ "time_cond_proj_dim": null,
60
+ "time_embedding_act_fn": null,
61
+ "time_embedding_dim": null,
62
+ "time_embedding_type": "positional",
63
+ "timestep_post_act": null,
64
+ "transformer_layers_per_block": 1,
65
+ "up_block_types": [
66
+ "UpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "CrossAttnUpBlock2D"
70
+ ],
71
+ "upcast_attention": false,
72
+ "use_linear_projection": true
73
+ }
checkpoint-1000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d87e876e7689d570404db959c3ba8b317f7b33d3aa188221148d9918d61523c
3
+ size 3463726504
checkpoint-1000/unet_ema/config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
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
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "decay": 0.9999,
30
+ "down_block_types": [
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "CrossAttnDownBlock2D",
34
+ "DownBlock2D"
35
+ ],
36
+ "downsample_padding": 1,
37
+ "dropout": 0.0,
38
+ "dual_cross_attention": false,
39
+ "encoder_hid_dim": null,
40
+ "encoder_hid_dim_type": null,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "in_channels": 4,
44
+ "inv_gamma": 1.0,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
49
+ "min_decay": 0.0,
50
+ "norm_eps": 1e-05,
51
+ "norm_num_groups": 32,
52
+ "num_attention_heads": null,
53
+ "num_class_embeds": null,
54
+ "only_cross_attention": false,
55
+ "optimization_step": 1000,
56
+ "out_channels": 4,
57
+ "power": 0.6666666666666666,
58
+ "projection_class_embeddings_input_dim": null,
59
+ "resnet_out_scale_factor": 1.0,
60
+ "resnet_skip_time_act": false,
61
+ "resnet_time_scale_shift": "default",
62
+ "reverse_transformer_layers_per_block": null,
63
+ "sample_size": 64,
64
+ "time_cond_proj_dim": null,
65
+ "time_embedding_act_fn": null,
66
+ "time_embedding_dim": null,
67
+ "time_embedding_type": "positional",
68
+ "timestep_post_act": null,
69
+ "transformer_layers_per_block": 1,
70
+ "up_block_types": [
71
+ "UpBlock2D",
72
+ "CrossAttnUpBlock2D",
73
+ "CrossAttnUpBlock2D",
74
+ "CrossAttnUpBlock2D"
75
+ ],
76
+ "upcast_attention": false,
77
+ "update_after_step": 0,
78
+ "use_ema_warmup": false,
79
+ "use_linear_projection": true
80
+ }
checkpoint-1000/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:299429647e5b372712db7feb9f30cd2c08f9c31f0407628046a6062bbe9de30a
3
+ size 3463726504
checkpoint-10000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdcfc2d457981febd7308b11fda2bc0602f9e7ef10061ab8081050f19f958419
3
+ size 6927867604
checkpoint-10000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c87572e736fa448045f6eeeddf7bc8be52f3b4bb1ded4916ccfc387e485e3b46
3
+ size 14344
checkpoint-10000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d31ad9a5150e341b638f838a47b3cb3db0d48efa493bcc8d1f8bf787b2c8cee3
3
+ size 1000
checkpoint-10000/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
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
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "DownBlock2D"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "flip_sin_to_cos": true,
41
+ "freq_shift": 0,
42
+ "in_channels": 4,
43
+ "layers_per_block": 2,
44
+ "mid_block_only_cross_attention": null,
45
+ "mid_block_scale_factor": 1,
46
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
47
+ "norm_eps": 1e-05,
48
+ "norm_num_groups": 32,
49
+ "num_attention_heads": null,
50
+ "num_class_embeds": null,
51
+ "only_cross_attention": false,
52
+ "out_channels": 4,
53
+ "projection_class_embeddings_input_dim": null,
54
+ "resnet_out_scale_factor": 1.0,
55
+ "resnet_skip_time_act": false,
56
+ "resnet_time_scale_shift": "default",
57
+ "reverse_transformer_layers_per_block": null,
58
+ "sample_size": 64,
59
+ "time_cond_proj_dim": null,
60
+ "time_embedding_act_fn": null,
61
+ "time_embedding_dim": null,
62
+ "time_embedding_type": "positional",
63
+ "timestep_post_act": null,
64
+ "transformer_layers_per_block": 1,
65
+ "up_block_types": [
66
+ "UpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "CrossAttnUpBlock2D"
70
+ ],
71
+ "upcast_attention": false,
72
+ "use_linear_projection": true
73
+ }
checkpoint-10000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1870293ad97a6041db8fa4192be326c1f76bac013278535dd41919172a86aba9
3
+ size 3463726504
checkpoint-10000/unet_ema/config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
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
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "decay": 0.9999,
30
+ "down_block_types": [
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "CrossAttnDownBlock2D",
34
+ "DownBlock2D"
35
+ ],
36
+ "downsample_padding": 1,
37
+ "dropout": 0.0,
38
+ "dual_cross_attention": false,
39
+ "encoder_hid_dim": null,
40
+ "encoder_hid_dim_type": null,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "in_channels": 4,
44
+ "inv_gamma": 1.0,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
49
+ "min_decay": 0.0,
50
+ "norm_eps": 1e-05,
51
+ "norm_num_groups": 32,
52
+ "num_attention_heads": null,
53
+ "num_class_embeds": null,
54
+ "only_cross_attention": false,
55
+ "optimization_step": 10000,
56
+ "out_channels": 4,
57
+ "power": 0.6666666666666666,
58
+ "projection_class_embeddings_input_dim": null,
59
+ "resnet_out_scale_factor": 1.0,
60
+ "resnet_skip_time_act": false,
61
+ "resnet_time_scale_shift": "default",
62
+ "reverse_transformer_layers_per_block": null,
63
+ "sample_size": 64,
64
+ "time_cond_proj_dim": null,
65
+ "time_embedding_act_fn": null,
66
+ "time_embedding_dim": null,
67
+ "time_embedding_type": "positional",
68
+ "timestep_post_act": null,
69
+ "transformer_layers_per_block": 1,
70
+ "up_block_types": [
71
+ "UpBlock2D",
72
+ "CrossAttnUpBlock2D",
73
+ "CrossAttnUpBlock2D",
74
+ "CrossAttnUpBlock2D"
75
+ ],
76
+ "upcast_attention": false,
77
+ "update_after_step": 0,
78
+ "use_ema_warmup": false,
79
+ "use_linear_projection": true
80
+ }
checkpoint-10000/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:864db28ad2f8c035b940e706f919801b11b9c4a565292240e230978cfee67186
3
+ size 3463726504
checkpoint-10500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c929787b624c58afce195e4a836aae27a535839866e2bb191cdc3991170326da
3
+ size 6927867604
checkpoint-10500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1942748712a7d41bfb33758dd1b52db762c08acec44179887bba3930cc1cb390
3
+ size 14344
checkpoint-10500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94d68e9fa853ae093658f50590cc9c32d2da56551802d5c8ad20ebcaf7c6eac6
3
+ size 1000
checkpoint-10500/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
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
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "DownBlock2D"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "flip_sin_to_cos": true,
41
+ "freq_shift": 0,
42
+ "in_channels": 4,
43
+ "layers_per_block": 2,
44
+ "mid_block_only_cross_attention": null,
45
+ "mid_block_scale_factor": 1,
46
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
47
+ "norm_eps": 1e-05,
48
+ "norm_num_groups": 32,
49
+ "num_attention_heads": null,
50
+ "num_class_embeds": null,
51
+ "only_cross_attention": false,
52
+ "out_channels": 4,
53
+ "projection_class_embeddings_input_dim": null,
54
+ "resnet_out_scale_factor": 1.0,
55
+ "resnet_skip_time_act": false,
56
+ "resnet_time_scale_shift": "default",
57
+ "reverse_transformer_layers_per_block": null,
58
+ "sample_size": 64,
59
+ "time_cond_proj_dim": null,
60
+ "time_embedding_act_fn": null,
61
+ "time_embedding_dim": null,
62
+ "time_embedding_type": "positional",
63
+ "timestep_post_act": null,
64
+ "transformer_layers_per_block": 1,
65
+ "up_block_types": [
66
+ "UpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "CrossAttnUpBlock2D"
70
+ ],
71
+ "upcast_attention": false,
72
+ "use_linear_projection": true
73
+ }
checkpoint-10500/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fe29a6d07726b05c3374db7631f134ecee2b82aee10f15040e6f44e93daa53f
3
+ size 3463726504
checkpoint-10500/unet_ema/config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
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
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "decay": 0.9999,
30
+ "down_block_types": [
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "CrossAttnDownBlock2D",
34
+ "DownBlock2D"
35
+ ],
36
+ "downsample_padding": 1,
37
+ "dropout": 0.0,
38
+ "dual_cross_attention": false,
39
+ "encoder_hid_dim": null,
40
+ "encoder_hid_dim_type": null,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "in_channels": 4,
44
+ "inv_gamma": 1.0,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
49
+ "min_decay": 0.0,
50
+ "norm_eps": 1e-05,
51
+ "norm_num_groups": 32,
52
+ "num_attention_heads": null,
53
+ "num_class_embeds": null,
54
+ "only_cross_attention": false,
55
+ "optimization_step": 10500,
56
+ "out_channels": 4,
57
+ "power": 0.6666666666666666,
58
+ "projection_class_embeddings_input_dim": null,
59
+ "resnet_out_scale_factor": 1.0,
60
+ "resnet_skip_time_act": false,
61
+ "resnet_time_scale_shift": "default",
62
+ "reverse_transformer_layers_per_block": null,
63
+ "sample_size": 64,
64
+ "time_cond_proj_dim": null,
65
+ "time_embedding_act_fn": null,
66
+ "time_embedding_dim": null,
67
+ "time_embedding_type": "positional",
68
+ "timestep_post_act": null,
69
+ "transformer_layers_per_block": 1,
70
+ "up_block_types": [
71
+ "UpBlock2D",
72
+ "CrossAttnUpBlock2D",
73
+ "CrossAttnUpBlock2D",
74
+ "CrossAttnUpBlock2D"
75
+ ],
76
+ "upcast_attention": false,
77
+ "update_after_step": 0,
78
+ "use_ema_warmup": false,
79
+ "use_linear_projection": true
80
+ }
checkpoint-10500/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b015519663756a87fe8c4221425533d66aab4287c566f5a9d184e2f3266b14eb
3
+ size 3463726504
checkpoint-11000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9f0b11d09a74e1f1d090de873242ef5cf86d2948a7ec7591c4521da37e62479
3
+ size 6927867604
checkpoint-11000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec72ca9df217279e39705df7cdee35aa2cc34f24a88a16a7e59958fed658c46d
3
+ size 14344
checkpoint-11000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7ba806b28f71e1e1cf1d42195652aa3e74d3e313c111b119d860e4f1aee287f
3
+ size 1000
checkpoint-11000/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
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
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "DownBlock2D"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "flip_sin_to_cos": true,
41
+ "freq_shift": 0,
42
+ "in_channels": 4,
43
+ "layers_per_block": 2,
44
+ "mid_block_only_cross_attention": null,
45
+ "mid_block_scale_factor": 1,
46
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
47
+ "norm_eps": 1e-05,
48
+ "norm_num_groups": 32,
49
+ "num_attention_heads": null,
50
+ "num_class_embeds": null,
51
+ "only_cross_attention": false,
52
+ "out_channels": 4,
53
+ "projection_class_embeddings_input_dim": null,
54
+ "resnet_out_scale_factor": 1.0,
55
+ "resnet_skip_time_act": false,
56
+ "resnet_time_scale_shift": "default",
57
+ "reverse_transformer_layers_per_block": null,
58
+ "sample_size": 64,
59
+ "time_cond_proj_dim": null,
60
+ "time_embedding_act_fn": null,
61
+ "time_embedding_dim": null,
62
+ "time_embedding_type": "positional",
63
+ "timestep_post_act": null,
64
+ "transformer_layers_per_block": 1,
65
+ "up_block_types": [
66
+ "UpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "CrossAttnUpBlock2D"
70
+ ],
71
+ "upcast_attention": false,
72
+ "use_linear_projection": true
73
+ }
checkpoint-11000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d209ad8aa95e40102ad26e4991525f1c59c357fdb510c612b1943ca3f3807261
3
+ size 3463726504
checkpoint-11000/unet_ema/config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
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
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "decay": 0.9999,
30
+ "down_block_types": [
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "CrossAttnDownBlock2D",
34
+ "DownBlock2D"
35
+ ],
36
+ "downsample_padding": 1,
37
+ "dropout": 0.0,
38
+ "dual_cross_attention": false,
39
+ "encoder_hid_dim": null,
40
+ "encoder_hid_dim_type": null,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "in_channels": 4,
44
+ "inv_gamma": 1.0,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
49
+ "min_decay": 0.0,
50
+ "norm_eps": 1e-05,
51
+ "norm_num_groups": 32,
52
+ "num_attention_heads": null,
53
+ "num_class_embeds": null,
54
+ "only_cross_attention": false,
55
+ "optimization_step": 11000,
56
+ "out_channels": 4,
57
+ "power": 0.6666666666666666,
58
+ "projection_class_embeddings_input_dim": null,
59
+ "resnet_out_scale_factor": 1.0,
60
+ "resnet_skip_time_act": false,
61
+ "resnet_time_scale_shift": "default",
62
+ "reverse_transformer_layers_per_block": null,
63
+ "sample_size": 64,
64
+ "time_cond_proj_dim": null,
65
+ "time_embedding_act_fn": null,
66
+ "time_embedding_dim": null,
67
+ "time_embedding_type": "positional",
68
+ "timestep_post_act": null,
69
+ "transformer_layers_per_block": 1,
70
+ "up_block_types": [
71
+ "UpBlock2D",
72
+ "CrossAttnUpBlock2D",
73
+ "CrossAttnUpBlock2D",
74
+ "CrossAttnUpBlock2D"
75
+ ],
76
+ "upcast_attention": false,
77
+ "update_after_step": 0,
78
+ "use_ema_warmup": false,
79
+ "use_linear_projection": true
80
+ }
checkpoint-11000/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba466bddc03c5594d6ec88565acdfaeeb201003c0a20d3247adcb934050ea996
3
+ size 3463726504
checkpoint-11500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4bbc6e6baf5082e39ec325fc631170d51cfaf60dbc6dd80d3d8c4c26f5e5d0a
3
+ size 6927867604
checkpoint-11500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:106bf018b1d1eccd8c5b1482a61e4f29de9a29f03ba1ac556be6396b31d5ad0a
3
+ size 14344
checkpoint-11500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7b2247bda89df10af46d8fc9946fb5ac6444c073272d5755453a114baf37790
3
+ size 1000
checkpoint-11500/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
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
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "DownBlock2D"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "flip_sin_to_cos": true,
41
+ "freq_shift": 0,
42
+ "in_channels": 4,
43
+ "layers_per_block": 2,
44
+ "mid_block_only_cross_attention": null,
45
+ "mid_block_scale_factor": 1,
46
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
47
+ "norm_eps": 1e-05,
48
+ "norm_num_groups": 32,
49
+ "num_attention_heads": null,
50
+ "num_class_embeds": null,
51
+ "only_cross_attention": false,
52
+ "out_channels": 4,
53
+ "projection_class_embeddings_input_dim": null,
54
+ "resnet_out_scale_factor": 1.0,
55
+ "resnet_skip_time_act": false,
56
+ "resnet_time_scale_shift": "default",
57
+ "reverse_transformer_layers_per_block": null,
58
+ "sample_size": 64,
59
+ "time_cond_proj_dim": null,
60
+ "time_embedding_act_fn": null,
61
+ "time_embedding_dim": null,
62
+ "time_embedding_type": "positional",
63
+ "timestep_post_act": null,
64
+ "transformer_layers_per_block": 1,
65
+ "up_block_types": [
66
+ "UpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "CrossAttnUpBlock2D"
70
+ ],
71
+ "upcast_attention": false,
72
+ "use_linear_projection": true
73
+ }
checkpoint-11500/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:946b89b03b4b686dda3f3d25c76a02713fae5acab2d7702f5ea10ebf98e60827
3
+ size 3463726504
checkpoint-11500/unet_ema/config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
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
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "decay": 0.9999,
30
+ "down_block_types": [
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "CrossAttnDownBlock2D",
34
+ "DownBlock2D"
35
+ ],
36
+ "downsample_padding": 1,
37
+ "dropout": 0.0,
38
+ "dual_cross_attention": false,
39
+ "encoder_hid_dim": null,
40
+ "encoder_hid_dim_type": null,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "in_channels": 4,
44
+ "inv_gamma": 1.0,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
49
+ "min_decay": 0.0,
50
+ "norm_eps": 1e-05,
51
+ "norm_num_groups": 32,
52
+ "num_attention_heads": null,
53
+ "num_class_embeds": null,
54
+ "only_cross_attention": false,
55
+ "optimization_step": 11500,
56
+ "out_channels": 4,
57
+ "power": 0.6666666666666666,
58
+ "projection_class_embeddings_input_dim": null,
59
+ "resnet_out_scale_factor": 1.0,
60
+ "resnet_skip_time_act": false,
61
+ "resnet_time_scale_shift": "default",
62
+ "reverse_transformer_layers_per_block": null,
63
+ "sample_size": 64,
64
+ "time_cond_proj_dim": null,
65
+ "time_embedding_act_fn": null,
66
+ "time_embedding_dim": null,
67
+ "time_embedding_type": "positional",
68
+ "timestep_post_act": null,
69
+ "transformer_layers_per_block": 1,
70
+ "up_block_types": [
71
+ "UpBlock2D",
72
+ "CrossAttnUpBlock2D",
73
+ "CrossAttnUpBlock2D",
74
+ "CrossAttnUpBlock2D"
75
+ ],
76
+ "upcast_attention": false,
77
+ "update_after_step": 0,
78
+ "use_ema_warmup": false,
79
+ "use_linear_projection": true
80
+ }
checkpoint-11500/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca3588c8b71b4fc9bb0ed2e7f31aaa65785264043f6180e2fd18a945f5838675
3
+ size 3463726504
checkpoint-12000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56974151a33dfc86022e31dc6d5f3002cbc3490a4fc97b39ef5de7cbab0b2b9a
3
+ size 6927867604
checkpoint-12000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a92deacc2e559cde1c4c080e74add80f2e63729cd61ea090d2796598b7e75d65
3
+ size 14344
checkpoint-12000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e71950f59e322ffbb0a94be88ee05554b97b740b97bea747e739593db11c43b9
3
+ size 1000
checkpoint-12000/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
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
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "DownBlock2D"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "flip_sin_to_cos": true,
41
+ "freq_shift": 0,
42
+ "in_channels": 4,
43
+ "layers_per_block": 2,
44
+ "mid_block_only_cross_attention": null,
45
+ "mid_block_scale_factor": 1,
46
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
47
+ "norm_eps": 1e-05,
48
+ "norm_num_groups": 32,
49
+ "num_attention_heads": null,
50
+ "num_class_embeds": null,
51
+ "only_cross_attention": false,
52
+ "out_channels": 4,
53
+ "projection_class_embeddings_input_dim": null,
54
+ "resnet_out_scale_factor": 1.0,
55
+ "resnet_skip_time_act": false,
56
+ "resnet_time_scale_shift": "default",
57
+ "reverse_transformer_layers_per_block": null,
58
+ "sample_size": 64,
59
+ "time_cond_proj_dim": null,
60
+ "time_embedding_act_fn": null,
61
+ "time_embedding_dim": null,
62
+ "time_embedding_type": "positional",
63
+ "timestep_post_act": null,
64
+ "transformer_layers_per_block": 1,
65
+ "up_block_types": [
66
+ "UpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "CrossAttnUpBlock2D"
70
+ ],
71
+ "upcast_attention": false,
72
+ "use_linear_projection": true
73
+ }
checkpoint-12000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7a148763702f8544778d8fd0d5ec368c6cd2ce6de46470fc27ff3377e833f1a
3
+ size 3463726504
checkpoint-12000/unet_ema/config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
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
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "decay": 0.9999,
30
+ "down_block_types": [
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "CrossAttnDownBlock2D",
34
+ "DownBlock2D"
35
+ ],
36
+ "downsample_padding": 1,
37
+ "dropout": 0.0,
38
+ "dual_cross_attention": false,
39
+ "encoder_hid_dim": null,
40
+ "encoder_hid_dim_type": null,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "in_channels": 4,
44
+ "inv_gamma": 1.0,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
49
+ "min_decay": 0.0,
50
+ "norm_eps": 1e-05,
51
+ "norm_num_groups": 32,
52
+ "num_attention_heads": null,
53
+ "num_class_embeds": null,
54
+ "only_cross_attention": false,
55
+ "optimization_step": 12000,
56
+ "out_channels": 4,
57
+ "power": 0.6666666666666666,
58
+ "projection_class_embeddings_input_dim": null,
59
+ "resnet_out_scale_factor": 1.0,
60
+ "resnet_skip_time_act": false,
61
+ "resnet_time_scale_shift": "default",
62
+ "reverse_transformer_layers_per_block": null,
63
+ "sample_size": 64,
64
+ "time_cond_proj_dim": null,
65
+ "time_embedding_act_fn": null,
66
+ "time_embedding_dim": null,
67
+ "time_embedding_type": "positional",
68
+ "timestep_post_act": null,
69
+ "transformer_layers_per_block": 1,
70
+ "up_block_types": [
71
+ "UpBlock2D",
72
+ "CrossAttnUpBlock2D",
73
+ "CrossAttnUpBlock2D",
74
+ "CrossAttnUpBlock2D"
75
+ ],
76
+ "upcast_attention": false,
77
+ "update_after_step": 0,
78
+ "use_ema_warmup": false,
79
+ "use_linear_projection": true
80
+ }
checkpoint-12000/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:053d9c3c0c2f60171be9b1ee1d7fadcefe1d78994321d0f6bd683e0b3f400eb8
3
+ size 3463726504
checkpoint-12500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:206c7e14278b8ca16b0a9cfdfd9e21fb7475c9f4b8f5a4e4310b586e7829dc26
3
+ size 6927867604
checkpoint-12500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01ae123d8d3ab0169fc5e8ebf349dd4793a2d2d0abb49c917ecdeb4b1f033156
3
+ size 14344
checkpoint-12500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7467495c6ea967b5801d100432185ae74ac62c2c3534d8f28d164e5eedcbe92d
3
+ size 1000
checkpoint-12500/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
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
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "DownBlock2D"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "flip_sin_to_cos": true,
41
+ "freq_shift": 0,
42
+ "in_channels": 4,
43
+ "layers_per_block": 2,
44
+ "mid_block_only_cross_attention": null,
45
+ "mid_block_scale_factor": 1,
46
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
47
+ "norm_eps": 1e-05,
48
+ "norm_num_groups": 32,
49
+ "num_attention_heads": null,
50
+ "num_class_embeds": null,
51
+ "only_cross_attention": false,
52
+ "out_channels": 4,
53
+ "projection_class_embeddings_input_dim": null,
54
+ "resnet_out_scale_factor": 1.0,
55
+ "resnet_skip_time_act": false,
56
+ "resnet_time_scale_shift": "default",
57
+ "reverse_transformer_layers_per_block": null,
58
+ "sample_size": 64,
59
+ "time_cond_proj_dim": null,
60
+ "time_embedding_act_fn": null,
61
+ "time_embedding_dim": null,
62
+ "time_embedding_type": "positional",
63
+ "timestep_post_act": null,
64
+ "transformer_layers_per_block": 1,
65
+ "up_block_types": [
66
+ "UpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "CrossAttnUpBlock2D"
70
+ ],
71
+ "upcast_attention": false,
72
+ "use_linear_projection": true
73
+ }
checkpoint-12500/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc17f3f7907c5a9413621a53f0297def71559c3383885bcd4469ee7ebf63493d
3
+ size 3463726504
checkpoint-12500/unet_ema/config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
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
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "decay": 0.9999,
30
+ "down_block_types": [
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "CrossAttnDownBlock2D",
34
+ "DownBlock2D"
35
+ ],
36
+ "downsample_padding": 1,
37
+ "dropout": 0.0,
38
+ "dual_cross_attention": false,
39
+ "encoder_hid_dim": null,
40
+ "encoder_hid_dim_type": null,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "in_channels": 4,
44
+ "inv_gamma": 1.0,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
49
+ "min_decay": 0.0,
50
+ "norm_eps": 1e-05,
51
+ "norm_num_groups": 32,
52
+ "num_attention_heads": null,
53
+ "num_class_embeds": null,
54
+ "only_cross_attention": false,
55
+ "optimization_step": 12500,
56
+ "out_channels": 4,
57
+ "power": 0.6666666666666666,
58
+ "projection_class_embeddings_input_dim": null,
59
+ "resnet_out_scale_factor": 1.0,
60
+ "resnet_skip_time_act": false,
61
+ "resnet_time_scale_shift": "default",
62
+ "reverse_transformer_layers_per_block": null,
63
+ "sample_size": 64,
64
+ "time_cond_proj_dim": null,
65
+ "time_embedding_act_fn": null,
66
+ "time_embedding_dim": null,
67
+ "time_embedding_type": "positional",
68
+ "timestep_post_act": null,
69
+ "transformer_layers_per_block": 1,
70
+ "up_block_types": [
71
+ "UpBlock2D",
72
+ "CrossAttnUpBlock2D",
73
+ "CrossAttnUpBlock2D",
74
+ "CrossAttnUpBlock2D"
75
+ ],
76
+ "upcast_attention": false,
77
+ "update_after_step": 0,
78
+ "use_ema_warmup": false,
79
+ "use_linear_projection": true
80
+ }
checkpoint-12500/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34e54d78e45e2dd786572bf305afe392f070553430b30237f39b934552482b07
3
+ size 3463726504