Hugging Face's logo

rgres
/
satellite_diffusion

Text-to-Image
Diffusers
Safetensors
StableDiffusionPipeline
stable-diffusion
stable-diffusion-diffusers
Inference Endpoints
Model card Files Community
rgres commited on
Commit
ff39a20
•
1 Parent(s): 1ceb4fb

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. .gitattributes +1 -0
  2. README.md +48 -0
  3. checkpoint-10000/optimizer.bin +3 -0
  4. checkpoint-10000/random_states_0.pkl +3 -0
  5. checkpoint-10000/scaler.pt +3 -0
  6. checkpoint-10000/scheduler.bin +3 -0
  7. checkpoint-10000/unet/config.json +71 -0
  8. checkpoint-10000/unet/diffusion_pytorch_model.safetensors +3 -0
  9. checkpoint-10000/unet_ema/config.json +78 -0
  10. checkpoint-10000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  11. checkpoint-11000/optimizer.bin +3 -0
  12. checkpoint-11000/random_states_0.pkl +3 -0
  13. checkpoint-11000/scaler.pt +3 -0
  14. checkpoint-11000/scheduler.bin +3 -0
  15. checkpoint-11000/unet/config.json +71 -0
  16. checkpoint-11000/unet/diffusion_pytorch_model.safetensors +3 -0
  17. checkpoint-11000/unet_ema/config.json +78 -0
  18. checkpoint-11000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  19. checkpoint-12000/optimizer.bin +3 -0
  20. checkpoint-12000/random_states_0.pkl +3 -0
  21. checkpoint-12000/scaler.pt +3 -0
  22. checkpoint-12000/scheduler.bin +3 -0
  23. checkpoint-12000/unet/config.json +71 -0
  24. checkpoint-12000/unet/diffusion_pytorch_model.safetensors +3 -0
  25. checkpoint-12000/unet_ema/config.json +78 -0
  26. checkpoint-12000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  27. checkpoint-13000/optimizer.bin +3 -0
  28. checkpoint-13000/random_states_0.pkl +3 -0
  29. checkpoint-13000/scaler.pt +3 -0
  30. checkpoint-13000/scheduler.bin +3 -0
  31. checkpoint-13000/unet/config.json +71 -0
  32. checkpoint-13000/unet/diffusion_pytorch_model.safetensors +3 -0
  33. checkpoint-13000/unet_ema/config.json +78 -0
  34. checkpoint-13000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  35. checkpoint-14000/optimizer.bin +3 -0
  36. checkpoint-14000/random_states_0.pkl +3 -0
  37. checkpoint-14000/scaler.pt +3 -0
  38. checkpoint-14000/scheduler.bin +3 -0
  39. checkpoint-14000/unet/config.json +71 -0
  40. checkpoint-14000/unet/diffusion_pytorch_model.safetensors +3 -0
  41. checkpoint-14000/unet_ema/config.json +78 -0
  42. checkpoint-14000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  43. checkpoint-15000/optimizer.bin +3 -0
  44. checkpoint-15000/random_states_0.pkl +3 -0
  45. checkpoint-15000/scaler.pt +3 -0
  46. checkpoint-15000/scheduler.bin +3 -0
  47. checkpoint-15000/unet/config.json +71 -0
  48. checkpoint-15000/unet/diffusion_pytorch_model.safetensors +3 -0
  49. checkpoint-15000/unet_ema/config.json +78 -0
  50. checkpoint-15000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ val_imgs_grid.png filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: creativeml-openrail-m
4
+ base_model: stabilityai/stable-diffusion-2
5
+ datasets:
6
+ - rgres/AerialDreams
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 - rgres/Seg2Map-finetuned
16
+
17
+ This pipeline was finetuned from **stabilityai/stable-diffusion-2** on the **rgres/AerialDreams** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ["Chemin de Saint-Antoine, Saint-Cyr-sur-Mer, Toulon, Var, Provence-Alpes-Cote d'Azur, Frane", 'Aerial view of Rond-Point de la 1e Armee Francaise - Lieutenant Paul Meyer, Mulhouse, Haut-Rhin, Grand Est, France metropolitaine, 68100, France', '31, Rue Molière, SS ace Coeur, Pyramides, La Roche-sur-Yon, Vendee, Pays de la Loire, France metropolitaine, 85000, France', 'Aerial view of Mourenx, Pau, Pyrenees-Atlantiques, Nouvelle-Aquitaine, France metropolitaine, 64150, France', '17 rue du moutier, Angousrine-Vileneuve-Les-Escaldes, Pyrenees Orientales, Occitanie, France metropolitaine, 66760, France']:
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("rgres/Seg2Map-finetuned", torch_dtype=torch.float16)
31
+ prompt = "Chemin de Saint-Antoine, Saint-Cyr-sur-Mer, Toulon, Var, Provence-Alpes-Cote d'Azur, Frane"
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: 1
41
+ * Learning rate: 1e-05
42
+ * Batch size: 1
43
+ * Gradient accumulation steps: 4
44
+ * Image resolution: 512
45
+ * Mixed-precision: fp16
46
+
47
+
48
+ More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/rubengres/text2image-fine-tune/runs/u9u76o1e).
checkpoint-10000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f78a7d03b64b3e37502b5610b3d12077758c170f9e8859d76094b3c1ca880e3
3
+ size 6927867091
checkpoint-10000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1597b9701d9297ed2cd58cea563e431f15ac5f7a88364e98bf4ed79ff799c2dd
3
+ size 14727
checkpoint-10000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa24a7ccfce356a1583e78c136eb82c89081166d4f3554ade432a0557e2a5961
3
+ size 557
checkpoint-10000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1ac838789823c0cd85e0866be8de301e624918a78578333980abe19b0dc7899
3
+ size 563
checkpoint-10000/unet/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2",
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
+ "dual_cross_attention": false,
37
+ "encoder_hid_dim": null,
38
+ "encoder_hid_dim_type": null,
39
+ "flip_sin_to_cos": true,
40
+ "freq_shift": 0,
41
+ "in_channels": 4,
42
+ "layers_per_block": 2,
43
+ "mid_block_only_cross_attention": null,
44
+ "mid_block_scale_factor": 1,
45
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
46
+ "norm_eps": 1e-05,
47
+ "norm_num_groups": 32,
48
+ "num_attention_heads": null,
49
+ "num_class_embeds": null,
50
+ "only_cross_attention": false,
51
+ "out_channels": 4,
52
+ "projection_class_embeddings_input_dim": null,
53
+ "resnet_out_scale_factor": 1.0,
54
+ "resnet_skip_time_act": false,
55
+ "resnet_time_scale_shift": "default",
56
+ "sample_size": 96,
57
+ "time_cond_proj_dim": null,
58
+ "time_embedding_act_fn": null,
59
+ "time_embedding_dim": null,
60
+ "time_embedding_type": "positional",
61
+ "timestep_post_act": null,
62
+ "transformer_layers_per_block": 1,
63
+ "up_block_types": [
64
+ "UpBlock2D",
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D",
67
+ "CrossAttnUpBlock2D"
68
+ ],
69
+ "upcast_attention": false,
70
+ "use_linear_projection": true
71
+ }
checkpoint-10000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bd07c1c74913bb251eab57a4b05ad0252e3426fe5feab375ce10f6d6b1df761
3
+ size 3463726504
checkpoint-10000/unet_ema/config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2",
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
+ "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
+ "inv_gamma": 1.0,
44
+ "layers_per_block": 2,
45
+ "mid_block_only_cross_attention": null,
46
+ "mid_block_scale_factor": 1,
47
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
48
+ "min_decay": 0.0,
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_attention_heads": null,
52
+ "num_class_embeds": null,
53
+ "only_cross_attention": false,
54
+ "optimization_step": 10000,
55
+ "out_channels": 4,
56
+ "power": 0.6666666666666666,
57
+ "projection_class_embeddings_input_dim": null,
58
+ "resnet_out_scale_factor": 1.0,
59
+ "resnet_skip_time_act": false,
60
+ "resnet_time_scale_shift": "default",
61
+ "sample_size": 96,
62
+ "time_cond_proj_dim": null,
63
+ "time_embedding_act_fn": null,
64
+ "time_embedding_dim": null,
65
+ "time_embedding_type": "positional",
66
+ "timestep_post_act": null,
67
+ "transformer_layers_per_block": 1,
68
+ "up_block_types": [
69
+ "UpBlock2D",
70
+ "CrossAttnUpBlock2D",
71
+ "CrossAttnUpBlock2D",
72
+ "CrossAttnUpBlock2D"
73
+ ],
74
+ "upcast_attention": false,
75
+ "update_after_step": 0,
76
+ "use_ema_warmup": false,
77
+ "use_linear_projection": true
78
+ }
checkpoint-10000/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:650eb40655352bd4f9090603832365144b7db39f95e8373410ac02eb6d1c0bec
3
+ size 3463726504
checkpoint-11000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2592862908a7746a4dcdfebd5a0a7c2217cf092d274ea65cfd2f190d3136278f
3
+ size 6927867091
checkpoint-11000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91be3a69ed7ae2251e033cbf77b07ce5066798b7c46aca51e53ecb4c762a9c07
3
+ size 14727
checkpoint-11000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57c4894759e734f0e89ead231f76ac405a604f6e445f3491f0af0afa37f7e6ea
3
+ size 557
checkpoint-11000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13125feec0588d182a29e1ce2499edee6397743de11761b57dbfbecc432b4f32
3
+ size 563
checkpoint-11000/unet/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2",
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
+ "dual_cross_attention": false,
37
+ "encoder_hid_dim": null,
38
+ "encoder_hid_dim_type": null,
39
+ "flip_sin_to_cos": true,
40
+ "freq_shift": 0,
41
+ "in_channels": 4,
42
+ "layers_per_block": 2,
43
+ "mid_block_only_cross_attention": null,
44
+ "mid_block_scale_factor": 1,
45
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
46
+ "norm_eps": 1e-05,
47
+ "norm_num_groups": 32,
48
+ "num_attention_heads": null,
49
+ "num_class_embeds": null,
50
+ "only_cross_attention": false,
51
+ "out_channels": 4,
52
+ "projection_class_embeddings_input_dim": null,
53
+ "resnet_out_scale_factor": 1.0,
54
+ "resnet_skip_time_act": false,
55
+ "resnet_time_scale_shift": "default",
56
+ "sample_size": 96,
57
+ "time_cond_proj_dim": null,
58
+ "time_embedding_act_fn": null,
59
+ "time_embedding_dim": null,
60
+ "time_embedding_type": "positional",
61
+ "timestep_post_act": null,
62
+ "transformer_layers_per_block": 1,
63
+ "up_block_types": [
64
+ "UpBlock2D",
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D",
67
+ "CrossAttnUpBlock2D"
68
+ ],
69
+ "upcast_attention": false,
70
+ "use_linear_projection": true
71
+ }
checkpoint-11000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb1f9dc8eeadccfa2577ecf0cf5dc330c62dac3a04e8be3818932bd56f24fc3c
3
+ size 3463726504
checkpoint-11000/unet_ema/config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2",
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
+ "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
+ "inv_gamma": 1.0,
44
+ "layers_per_block": 2,
45
+ "mid_block_only_cross_attention": null,
46
+ "mid_block_scale_factor": 1,
47
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
48
+ "min_decay": 0.0,
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_attention_heads": null,
52
+ "num_class_embeds": null,
53
+ "only_cross_attention": false,
54
+ "optimization_step": 11000,
55
+ "out_channels": 4,
56
+ "power": 0.6666666666666666,
57
+ "projection_class_embeddings_input_dim": null,
58
+ "resnet_out_scale_factor": 1.0,
59
+ "resnet_skip_time_act": false,
60
+ "resnet_time_scale_shift": "default",
61
+ "sample_size": 96,
62
+ "time_cond_proj_dim": null,
63
+ "time_embedding_act_fn": null,
64
+ "time_embedding_dim": null,
65
+ "time_embedding_type": "positional",
66
+ "timestep_post_act": null,
67
+ "transformer_layers_per_block": 1,
68
+ "up_block_types": [
69
+ "UpBlock2D",
70
+ "CrossAttnUpBlock2D",
71
+ "CrossAttnUpBlock2D",
72
+ "CrossAttnUpBlock2D"
73
+ ],
74
+ "upcast_attention": false,
75
+ "update_after_step": 0,
76
+ "use_ema_warmup": false,
77
+ "use_linear_projection": true
78
+ }
checkpoint-11000/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57cdb060205f9b2c7b0f068461d32ab5f1d38abcf093317dc1447afa74fcfbd0
3
+ size 3463726504
checkpoint-12000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3ed85ad6f1ed4ca81103360c493a2ebff299001b8bffbb0f372f7e1e33fd761
3
+ size 6927867091
checkpoint-12000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdf2309606b400a78b5fdd5bd14003fae84712f19f04c23f5295a84278f20f80
3
+ size 14727
checkpoint-12000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eb7f76ce91948e237d8ffe52606c51e1d5e49f3deb157cd9d928486182e9b23
3
+ size 557
checkpoint-12000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29b494d1a21a65e3748eb85926da60846dfe50ea84ed66cb9a8f8fa36c9be830
3
+ size 563
checkpoint-12000/unet/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2",
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
+ "dual_cross_attention": false,
37
+ "encoder_hid_dim": null,
38
+ "encoder_hid_dim_type": null,
39
+ "flip_sin_to_cos": true,
40
+ "freq_shift": 0,
41
+ "in_channels": 4,
42
+ "layers_per_block": 2,
43
+ "mid_block_only_cross_attention": null,
44
+ "mid_block_scale_factor": 1,
45
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
46
+ "norm_eps": 1e-05,
47
+ "norm_num_groups": 32,
48
+ "num_attention_heads": null,
49
+ "num_class_embeds": null,
50
+ "only_cross_attention": false,
51
+ "out_channels": 4,
52
+ "projection_class_embeddings_input_dim": null,
53
+ "resnet_out_scale_factor": 1.0,
54
+ "resnet_skip_time_act": false,
55
+ "resnet_time_scale_shift": "default",
56
+ "sample_size": 96,
57
+ "time_cond_proj_dim": null,
58
+ "time_embedding_act_fn": null,
59
+ "time_embedding_dim": null,
60
+ "time_embedding_type": "positional",
61
+ "timestep_post_act": null,
62
+ "transformer_layers_per_block": 1,
63
+ "up_block_types": [
64
+ "UpBlock2D",
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D",
67
+ "CrossAttnUpBlock2D"
68
+ ],
69
+ "upcast_attention": false,
70
+ "use_linear_projection": true
71
+ }
checkpoint-12000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00654cf65765996e729beb21e6740696a81e7688fe982f8cc43239f883208d5c
3
+ size 3463726504
checkpoint-12000/unet_ema/config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2",
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
+ "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
+ "inv_gamma": 1.0,
44
+ "layers_per_block": 2,
45
+ "mid_block_only_cross_attention": null,
46
+ "mid_block_scale_factor": 1,
47
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
48
+ "min_decay": 0.0,
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_attention_heads": null,
52
+ "num_class_embeds": null,
53
+ "only_cross_attention": false,
54
+ "optimization_step": 12000,
55
+ "out_channels": 4,
56
+ "power": 0.6666666666666666,
57
+ "projection_class_embeddings_input_dim": null,
58
+ "resnet_out_scale_factor": 1.0,
59
+ "resnet_skip_time_act": false,
60
+ "resnet_time_scale_shift": "default",
61
+ "sample_size": 96,
62
+ "time_cond_proj_dim": null,
63
+ "time_embedding_act_fn": null,
64
+ "time_embedding_dim": null,
65
+ "time_embedding_type": "positional",
66
+ "timestep_post_act": null,
67
+ "transformer_layers_per_block": 1,
68
+ "up_block_types": [
69
+ "UpBlock2D",
70
+ "CrossAttnUpBlock2D",
71
+ "CrossAttnUpBlock2D",
72
+ "CrossAttnUpBlock2D"
73
+ ],
74
+ "upcast_attention": false,
75
+ "update_after_step": 0,
76
+ "use_ema_warmup": false,
77
+ "use_linear_projection": true
78
+ }
checkpoint-12000/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49cb0190d134ebdda5f7c16fdbc6bab95239e2c5169ea4b8f7669b95b2904821
3
+ size 3463726504
checkpoint-13000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcdb82dc117ff51dcc8ae6d2629369a028f8d165e5e6697d07a21535e964661f
3
+ size 6927867091
checkpoint-13000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29ff25faf6db55fad5138376586b3913fcfcfa72fa4b69622e36f50def6ec835
3
+ size 14727
checkpoint-13000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cc62fcf9eb58b07124e506e408a3bdac7ac771c62ea2c7a380549be2f443822
3
+ size 557
checkpoint-13000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2e4bced6db6097d462daaaa2831a3aef134b5ec78fed884824373b7d9118809
3
+ size 563
checkpoint-13000/unet/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2",
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
+ "dual_cross_attention": false,
37
+ "encoder_hid_dim": null,
38
+ "encoder_hid_dim_type": null,
39
+ "flip_sin_to_cos": true,
40
+ "freq_shift": 0,
41
+ "in_channels": 4,
42
+ "layers_per_block": 2,
43
+ "mid_block_only_cross_attention": null,
44
+ "mid_block_scale_factor": 1,
45
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
46
+ "norm_eps": 1e-05,
47
+ "norm_num_groups": 32,
48
+ "num_attention_heads": null,
49
+ "num_class_embeds": null,
50
+ "only_cross_attention": false,
51
+ "out_channels": 4,
52
+ "projection_class_embeddings_input_dim": null,
53
+ "resnet_out_scale_factor": 1.0,
54
+ "resnet_skip_time_act": false,
55
+ "resnet_time_scale_shift": "default",
56
+ "sample_size": 96,
57
+ "time_cond_proj_dim": null,
58
+ "time_embedding_act_fn": null,
59
+ "time_embedding_dim": null,
60
+ "time_embedding_type": "positional",
61
+ "timestep_post_act": null,
62
+ "transformer_layers_per_block": 1,
63
+ "up_block_types": [
64
+ "UpBlock2D",
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D",
67
+ "CrossAttnUpBlock2D"
68
+ ],
69
+ "upcast_attention": false,
70
+ "use_linear_projection": true
71
+ }
checkpoint-13000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:111c14a5f20d6d65fd97f7d33d66a0df09d72eacce9f0888c1a4f5e5f791959f
3
+ size 3463726504
checkpoint-13000/unet_ema/config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2",
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
+ "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
+ "inv_gamma": 1.0,
44
+ "layers_per_block": 2,
45
+ "mid_block_only_cross_attention": null,
46
+ "mid_block_scale_factor": 1,
47
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
48
+ "min_decay": 0.0,
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_attention_heads": null,
52
+ "num_class_embeds": null,
53
+ "only_cross_attention": false,
54
+ "optimization_step": 13000,
55
+ "out_channels": 4,
56
+ "power": 0.6666666666666666,
57
+ "projection_class_embeddings_input_dim": null,
58
+ "resnet_out_scale_factor": 1.0,
59
+ "resnet_skip_time_act": false,
60
+ "resnet_time_scale_shift": "default",
61
+ "sample_size": 96,
62
+ "time_cond_proj_dim": null,
63
+ "time_embedding_act_fn": null,
64
+ "time_embedding_dim": null,
65
+ "time_embedding_type": "positional",
66
+ "timestep_post_act": null,
67
+ "transformer_layers_per_block": 1,
68
+ "up_block_types": [
69
+ "UpBlock2D",
70
+ "CrossAttnUpBlock2D",
71
+ "CrossAttnUpBlock2D",
72
+ "CrossAttnUpBlock2D"
73
+ ],
74
+ "upcast_attention": false,
75
+ "update_after_step": 0,
76
+ "use_ema_warmup": false,
77
+ "use_linear_projection": true
78
+ }
checkpoint-13000/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36d1de91dc8b07923ecf777a5524c9a27325a725b7f3517fcbe17d7b679753af
3
+ size 3463726504
checkpoint-14000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd185a58879c0c9d0d9269968ef6233a0860592ee6e18f1dc098f0c5c42e507e
3
+ size 6927867091
checkpoint-14000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09453653af18592302146074cb196d0c29d436d4cdcdd9c22791adb48aacba80
3
+ size 14727
checkpoint-14000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f390441bf3e035f69c08c18672628618848b1ac92b1c38f089606ee455951081
3
+ size 557
checkpoint-14000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f679bd63765b191e13032dd5d46de2621cc142f3f774ce3a44ce69543a2f5748
3
+ size 563
checkpoint-14000/unet/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2",
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
+ "dual_cross_attention": false,
37
+ "encoder_hid_dim": null,
38
+ "encoder_hid_dim_type": null,
39
+ "flip_sin_to_cos": true,
40
+ "freq_shift": 0,
41
+ "in_channels": 4,
42
+ "layers_per_block": 2,
43
+ "mid_block_only_cross_attention": null,
44
+ "mid_block_scale_factor": 1,
45
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
46
+ "norm_eps": 1e-05,
47
+ "norm_num_groups": 32,
48
+ "num_attention_heads": null,
49
+ "num_class_embeds": null,
50
+ "only_cross_attention": false,
51
+ "out_channels": 4,
52
+ "projection_class_embeddings_input_dim": null,
53
+ "resnet_out_scale_factor": 1.0,
54
+ "resnet_skip_time_act": false,
55
+ "resnet_time_scale_shift": "default",
56
+ "sample_size": 96,
57
+ "time_cond_proj_dim": null,
58
+ "time_embedding_act_fn": null,
59
+ "time_embedding_dim": null,
60
+ "time_embedding_type": "positional",
61
+ "timestep_post_act": null,
62
+ "transformer_layers_per_block": 1,
63
+ "up_block_types": [
64
+ "UpBlock2D",
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D",
67
+ "CrossAttnUpBlock2D"
68
+ ],
69
+ "upcast_attention": false,
70
+ "use_linear_projection": true
71
+ }
checkpoint-14000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34076035ab7c85a089f1ceb40dd5eccbd2a01e5555044e15d14027681daa11a5
3
+ size 3463726504
checkpoint-14000/unet_ema/config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2",
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
+ "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
+ "inv_gamma": 1.0,
44
+ "layers_per_block": 2,
45
+ "mid_block_only_cross_attention": null,
46
+ "mid_block_scale_factor": 1,
47
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
48
+ "min_decay": 0.0,
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_attention_heads": null,
52
+ "num_class_embeds": null,
53
+ "only_cross_attention": false,
54
+ "optimization_step": 14000,
55
+ "out_channels": 4,
56
+ "power": 0.6666666666666666,
57
+ "projection_class_embeddings_input_dim": null,
58
+ "resnet_out_scale_factor": 1.0,
59
+ "resnet_skip_time_act": false,
60
+ "resnet_time_scale_shift": "default",
61
+ "sample_size": 96,
62
+ "time_cond_proj_dim": null,
63
+ "time_embedding_act_fn": null,
64
+ "time_embedding_dim": null,
65
+ "time_embedding_type": "positional",
66
+ "timestep_post_act": null,
67
+ "transformer_layers_per_block": 1,
68
+ "up_block_types": [
69
+ "UpBlock2D",
70
+ "CrossAttnUpBlock2D",
71
+ "CrossAttnUpBlock2D",
72
+ "CrossAttnUpBlock2D"
73
+ ],
74
+ "upcast_attention": false,
75
+ "update_after_step": 0,
76
+ "use_ema_warmup": false,
77
+ "use_linear_projection": true
78
+ }
checkpoint-14000/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e55bdac1f5d7f51868270c00d7e428032521ae2f2b7f35a032b4e04e3af9e174
3
+ size 3463726504
checkpoint-15000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1114bb506ffe1ed46c834beb4e7560d1ace3592089dc892a66a992acd9c8ef46
3
+ size 6927867091
checkpoint-15000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fa3209b66e6a30401b2ddae38f7a000f84adc8e253c65e2571510d1afebc57e
3
+ size 14727
checkpoint-15000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc36770c4ba26cb283c153684420021bb79dd149e6e4cf3f3c54f5f6aa8e0b3e
3
+ size 557
checkpoint-15000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7feb664d17d81cb3613563e794c32d73395e41b364ec6e6ca0da59f6537b9a23
3
+ size 563
checkpoint-15000/unet/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2",
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
+ "dual_cross_attention": false,
37
+ "encoder_hid_dim": null,
38
+ "encoder_hid_dim_type": null,
39
+ "flip_sin_to_cos": true,
40
+ "freq_shift": 0,
41
+ "in_channels": 4,
42
+ "layers_per_block": 2,
43
+ "mid_block_only_cross_attention": null,
44
+ "mid_block_scale_factor": 1,
45
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
46
+ "norm_eps": 1e-05,
47
+ "norm_num_groups": 32,
48
+ "num_attention_heads": null,
49
+ "num_class_embeds": null,
50
+ "only_cross_attention": false,
51
+ "out_channels": 4,
52
+ "projection_class_embeddings_input_dim": null,
53
+ "resnet_out_scale_factor": 1.0,
54
+ "resnet_skip_time_act": false,
55
+ "resnet_time_scale_shift": "default",
56
+ "sample_size": 96,
57
+ "time_cond_proj_dim": null,
58
+ "time_embedding_act_fn": null,
59
+ "time_embedding_dim": null,
60
+ "time_embedding_type": "positional",
61
+ "timestep_post_act": null,
62
+ "transformer_layers_per_block": 1,
63
+ "up_block_types": [
64
+ "UpBlock2D",
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D",
67
+ "CrossAttnUpBlock2D"
68
+ ],
69
+ "upcast_attention": false,
70
+ "use_linear_projection": true
71
+ }
checkpoint-15000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:779cf8401a7ae5bc8f352d03d604815e979d0f0b8b9b09bd56967a3d5880d9db
3
+ size 3463726504
checkpoint-15000/unet_ema/config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2",
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
+ "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
+ "inv_gamma": 1.0,
44
+ "layers_per_block": 2,
45
+ "mid_block_only_cross_attention": null,
46
+ "mid_block_scale_factor": 1,
47
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
48
+ "min_decay": 0.0,
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_attention_heads": null,
52
+ "num_class_embeds": null,
53
+ "only_cross_attention": false,
54
+ "optimization_step": 15000,
55
+ "out_channels": 4,
56
+ "power": 0.6666666666666666,
57
+ "projection_class_embeddings_input_dim": null,
58
+ "resnet_out_scale_factor": 1.0,
59
+ "resnet_skip_time_act": false,
60
+ "resnet_time_scale_shift": "default",
61
+ "sample_size": 96,
62
+ "time_cond_proj_dim": null,
63
+ "time_embedding_act_fn": null,
64
+ "time_embedding_dim": null,
65
+ "time_embedding_type": "positional",
66
+ "timestep_post_act": null,
67
+ "transformer_layers_per_block": 1,
68
+ "up_block_types": [
69
+ "UpBlock2D",
70
+ "CrossAttnUpBlock2D",
71
+ "CrossAttnUpBlock2D",
72
+ "CrossAttnUpBlock2D"
73
+ ],
74
+ "upcast_attention": false,
75
+ "update_after_step": 0,
76
+ "use_ema_warmup": false,
77
+ "use_linear_projection": true
78
+ }
checkpoint-15000/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12a9e77f9ff3afb4bbf5d87adea9929da740f8ad4ad2b9761e8f4b564f1f1eb4
3
+ size 3463726504