Hugging Face's logo

SolVerum
/
AUG23TRAINING_V2

Text-to-Image
Diffusers
Safetensors
StableDiffusionXLPipeline
stable-diffusion-xl
stable-diffusion-xl-diffusers
diffusers-training
Model card Files
xet
Community
zarskiii commited on
Commit
5da349e
·
verified ·
1 Parent(s): 47c601e

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 +45 -0
  2. checkpoint-1000/optimizer.bin +3 -0
  3. checkpoint-1000/random_states_0.pkl +3 -0
  4. checkpoint-1000/scaler.pt +3 -0
  5. checkpoint-1000/scheduler.bin +3 -0
  6. checkpoint-1000/unet/config.json +73 -0
  7. checkpoint-1000/unet/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
  8. checkpoint-1000/unet/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
  9. checkpoint-1000/unet/diffusion_pytorch_model.safetensors.index.json +0 -0
  10. checkpoint-1000/unet_ema/config.json +80 -0
  11. checkpoint-1000/unet_ema/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
  12. checkpoint-1000/unet_ema/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
  13. checkpoint-1000/unet_ema/diffusion_pytorch_model.safetensors.index.json +0 -0
  14. checkpoint-1500/optimizer.bin +3 -0
  15. checkpoint-1500/random_states_0.pkl +3 -0
  16. checkpoint-1500/scaler.pt +3 -0
  17. checkpoint-1500/scheduler.bin +3 -0
  18. checkpoint-1500/unet/config.json +73 -0
  19. checkpoint-1500/unet/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
  20. checkpoint-1500/unet/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
  21. checkpoint-1500/unet/diffusion_pytorch_model.safetensors.index.json +0 -0
  22. checkpoint-1500/unet_ema/config.json +80 -0
  23. checkpoint-1500/unet_ema/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
  24. checkpoint-1500/unet_ema/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
  25. checkpoint-1500/unet_ema/diffusion_pytorch_model.safetensors.index.json +0 -0
  26. checkpoint-2000/optimizer.bin +3 -0
  27. checkpoint-2000/random_states_0.pkl +3 -0
  28. checkpoint-2000/scaler.pt +3 -0
  29. checkpoint-2000/scheduler.bin +3 -0
  30. checkpoint-2000/unet/config.json +73 -0
  31. checkpoint-2000/unet/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
  32. checkpoint-2000/unet/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
  33. checkpoint-2000/unet/diffusion_pytorch_model.safetensors.index.json +0 -0
  34. checkpoint-2000/unet_ema/config.json +80 -0
  35. checkpoint-2000/unet_ema/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
  36. checkpoint-2000/unet_ema/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
  37. checkpoint-2000/unet_ema/diffusion_pytorch_model.safetensors.index.json +0 -0
  38. checkpoint-500/optimizer.bin +3 -0
  39. checkpoint-500/random_states_0.pkl +3 -0
  40. checkpoint-500/scaler.pt +3 -0
  41. checkpoint-500/scheduler.bin +3 -0
  42. checkpoint-500/unet/config.json +73 -0
  43. checkpoint-500/unet/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
  44. checkpoint-500/unet/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
  45. checkpoint-500/unet/diffusion_pytorch_model.safetensors.index.json +0 -0
  46. checkpoint-500/unet_ema/config.json +80 -0
  47. checkpoint-500/unet_ema/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
  48. checkpoint-500/unet_ema/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
  49. checkpoint-500/unet_ema/diffusion_pytorch_model.safetensors.index.json +0 -0
  50. image_0.png +0 -0
README.md ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
3
+ library_name: diffusers
4
+ license: creativeml-openrail-m
5
+ tags:
6
+ - stable-diffusion-xl
7
+ - stable-diffusion-xl-diffusers
8
+ - text-to-image
9
+ - diffusers-training
10
+ - diffusers
11
+ inference: true
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the training script had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+
18
+ # Text-to-image finetuning - SolVerum/AUG23TRAINING_V2
19
+
20
+ This pipeline was finetuned from **stabilityai/stable-diffusion-xl-base-1.0** on the **SolVerum/MCSkins8.0** dataset. Below are some example images generated with the finetuned pipeline using the following prompt: Girl with long purple hair wearing a floral top. LAYER Hair and top details:
21
+
22
+ ![img_0](./image_0.png)
23
+ ![img_1](./image_1.png)
24
+ ![img_2](./image_2.png)
25
+ ![img_3](./image_3.png)
26
+
27
+
28
+ Special VAE used for training: None.
29
+
30
+
31
+ ## Intended uses & limitations
32
+
33
+ #### How to use
34
+
35
+ ```python
36
+ # TODO: add an example code snippet for running this diffusion pipeline
37
+ ```
38
+
39
+ #### Limitations and bias
40
+
41
+ [TODO: provide examples of latent issues and potential remediations]
42
+
43
+ ## Training details
44
+
45
+ [TODO: describe the data used to train the model]
checkpoint-1000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2f35b806697b54f5e8653b86faeb0cd0e8bf39bc2fa90bc31b28c192712a3aa
3
+ size 20541173898
checkpoint-1000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a42645b476c05dc1218f74e1e00313f9a969f30522e7d95cd5a3e10fe97caa21
3
+ size 14344
checkpoint-1000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d8fdcd0311eba9854fff738038ed4c1a269832665b4d88ba4e4e3d02a1a7e0e
3
+ size 988
checkpoint-1000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd24f729d84b4242b6c3afd54d49f9f9a90b357c89e1497e1cbb3d243bd159f9
3
+ size 1000
checkpoint-1000/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.31.0.dev0",
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
+ }
checkpoint-1000/unet/diffusion_pytorch_model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ebf93840cf9e88f3a22b74dbcec2366479c82df4b1b82dc24e0758e93b19b80
3
+ size 9988139160
checkpoint-1000/unet/diffusion_pytorch_model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8120d9d82905f6729e07308709b3f48e355d0f1df60adb8d954eca389d5a905
3
+ size 281938304
checkpoint-1000/unet/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/unet_ema/config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.31.0.dev0",
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
+ "decay": 0.9999,
28
+ "down_block_types": [
29
+ "DownBlock2D",
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D"
32
+ ],
33
+ "downsample_padding": 1,
34
+ "dropout": 0.0,
35
+ "dual_cross_attention": false,
36
+ "encoder_hid_dim": null,
37
+ "encoder_hid_dim_type": null,
38
+ "flip_sin_to_cos": true,
39
+ "freq_shift": 0,
40
+ "in_channels": 4,
41
+ "inv_gamma": 1.0,
42
+ "layers_per_block": 2,
43
+ "mid_block_only_cross_attention": null,
44
+ "mid_block_scale_factor": 1,
45
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
46
+ "min_decay": 0.0,
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
+ "optimization_step": 1000,
53
+ "out_channels": 4,
54
+ "power": 0.6666666666666666,
55
+ "projection_class_embeddings_input_dim": 2816,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "reverse_transformer_layers_per_block": null,
60
+ "sample_size": 128,
61
+ "time_cond_proj_dim": null,
62
+ "time_embedding_act_fn": null,
63
+ "time_embedding_dim": null,
64
+ "time_embedding_type": "positional",
65
+ "timestep_post_act": null,
66
+ "transformer_layers_per_block": [
67
+ 1,
68
+ 2,
69
+ 10
70
+ ],
71
+ "up_block_types": [
72
+ "CrossAttnUpBlock2D",
73
+ "CrossAttnUpBlock2D",
74
+ "UpBlock2D"
75
+ ],
76
+ "upcast_attention": null,
77
+ "update_after_step": 0,
78
+ "use_ema_warmup": false,
79
+ "use_linear_projection": true
80
+ }
checkpoint-1000/unet_ema/diffusion_pytorch_model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c2bd8fe8334ed44063707881ecc2b6f19e24832b968b7e825d256c2669fc1a3
3
+ size 9988139160
checkpoint-1000/unet_ema/diffusion_pytorch_model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:208e5086a347fa2fd05532742bb6242b9165fd265be6e1e501733dd17aae1bf5
3
+ size 281938304
checkpoint-1000/unet_ema/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:711e75f0725d3a84b6326687cfc742a3deb0f8401bf892f32208f3c85af7c367
3
+ size 20541173898
checkpoint-1500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c234fcd52ead602b283f0416a0d6fa130035743ea2c1091458dfd0b5fc10fd7
3
+ size 14408
checkpoint-1500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2a4b6e0ef05ca249f2d6b7f9f3ad1dff81e55842a962df795bb9740c17c8e92
3
+ size 988
checkpoint-1500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:187fe63402a1553bfe489819164da9d2ed6b6fdf7eadfcac90fd63b2d382bbf5
3
+ size 1000
checkpoint-1500/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.31.0.dev0",
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
+ }
checkpoint-1500/unet/diffusion_pytorch_model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c497c0e1b467c2a7a79bd8905f075edf3d34d71b0c11ffb4075fcf6770f26ed
3
+ size 9988139160
checkpoint-1500/unet/diffusion_pytorch_model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf94c49c2a83f23f6cc25ab38caefb59ef250799832c713673bde5aa91c499e0
3
+ size 281938304
checkpoint-1500/unet/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1500/unet_ema/config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.31.0.dev0",
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
+ "decay": 0.9999,
28
+ "down_block_types": [
29
+ "DownBlock2D",
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D"
32
+ ],
33
+ "downsample_padding": 1,
34
+ "dropout": 0.0,
35
+ "dual_cross_attention": false,
36
+ "encoder_hid_dim": null,
37
+ "encoder_hid_dim_type": null,
38
+ "flip_sin_to_cos": true,
39
+ "freq_shift": 0,
40
+ "in_channels": 4,
41
+ "inv_gamma": 1.0,
42
+ "layers_per_block": 2,
43
+ "mid_block_only_cross_attention": null,
44
+ "mid_block_scale_factor": 1,
45
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
46
+ "min_decay": 0.0,
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
+ "optimization_step": 1500,
53
+ "out_channels": 4,
54
+ "power": 0.6666666666666666,
55
+ "projection_class_embeddings_input_dim": 2816,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "reverse_transformer_layers_per_block": null,
60
+ "sample_size": 128,
61
+ "time_cond_proj_dim": null,
62
+ "time_embedding_act_fn": null,
63
+ "time_embedding_dim": null,
64
+ "time_embedding_type": "positional",
65
+ "timestep_post_act": null,
66
+ "transformer_layers_per_block": [
67
+ 1,
68
+ 2,
69
+ 10
70
+ ],
71
+ "up_block_types": [
72
+ "CrossAttnUpBlock2D",
73
+ "CrossAttnUpBlock2D",
74
+ "UpBlock2D"
75
+ ],
76
+ "upcast_attention": null,
77
+ "update_after_step": 0,
78
+ "use_ema_warmup": false,
79
+ "use_linear_projection": true
80
+ }
checkpoint-1500/unet_ema/diffusion_pytorch_model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66161dee083fc362520786c9de0ee1312bf5043bd20f7796700eff17fb9bcb2e
3
+ size 9988139160
checkpoint-1500/unet_ema/diffusion_pytorch_model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06553def984fe9bdf077ea50d95721c8a8025e92d1552ca3582eeec585ca16a8
3
+ size 281938304
checkpoint-1500/unet_ema/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0162f908ff00f803e11f01ddc3b2425e3780ce1254feb07682d8df1e97f95a5
3
+ size 20541173898
checkpoint-2000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41c165d2ae93318e9dd7e0fdb9cf8c41421730cf3fa7af568b2c0fb50da3573a
3
+ size 14408
checkpoint-2000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c50a9cebe5d66d453d25b140738bff479749ac03e0a43597d8776bc22f6ed0c
3
+ size 988
checkpoint-2000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdca87149a506f9b3d6812b9c013f2016b4da8466fed18ba980a21bc35dab5f1
3
+ size 1000
checkpoint-2000/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.31.0.dev0",
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
+ }
checkpoint-2000/unet/diffusion_pytorch_model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a32891b5899c10efb055befaf577fe19cebc01515738323d10a5e5a66f4f7a9
3
+ size 9988139160
checkpoint-2000/unet/diffusion_pytorch_model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acacc0151f6f8ff731982c432bb55b5cd696c1150da0ba5b918b7f9431f4dabd
3
+ size 281938304
checkpoint-2000/unet/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2000/unet_ema/config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.31.0.dev0",
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
+ "decay": 0.9999,
28
+ "down_block_types": [
29
+ "DownBlock2D",
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D"
32
+ ],
33
+ "downsample_padding": 1,
34
+ "dropout": 0.0,
35
+ "dual_cross_attention": false,
36
+ "encoder_hid_dim": null,
37
+ "encoder_hid_dim_type": null,
38
+ "flip_sin_to_cos": true,
39
+ "freq_shift": 0,
40
+ "in_channels": 4,
41
+ "inv_gamma": 1.0,
42
+ "layers_per_block": 2,
43
+ "mid_block_only_cross_attention": null,
44
+ "mid_block_scale_factor": 1,
45
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
46
+ "min_decay": 0.0,
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
+ "optimization_step": 2000,
53
+ "out_channels": 4,
54
+ "power": 0.6666666666666666,
55
+ "projection_class_embeddings_input_dim": 2816,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "reverse_transformer_layers_per_block": null,
60
+ "sample_size": 128,
61
+ "time_cond_proj_dim": null,
62
+ "time_embedding_act_fn": null,
63
+ "time_embedding_dim": null,
64
+ "time_embedding_type": "positional",
65
+ "timestep_post_act": null,
66
+ "transformer_layers_per_block": [
67
+ 1,
68
+ 2,
69
+ 10
70
+ ],
71
+ "up_block_types": [
72
+ "CrossAttnUpBlock2D",
73
+ "CrossAttnUpBlock2D",
74
+ "UpBlock2D"
75
+ ],
76
+ "upcast_attention": null,
77
+ "update_after_step": 0,
78
+ "use_ema_warmup": false,
79
+ "use_linear_projection": true
80
+ }
checkpoint-2000/unet_ema/diffusion_pytorch_model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9bd7adf2c15954008949fb06bd3b3ab2ffca584baeee964c41a0090118e5473
3
+ size 9988139160
checkpoint-2000/unet_ema/diffusion_pytorch_model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5159ea9def7c90baf7b3b27387f11f82c9a0fbddb1310a04e6b26123da7f5c4c
3
+ size 281938304
checkpoint-2000/unet_ema/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fe0ac261560fd39037d0327e10350736d74f7132a741aa31c805e18af46ce87
3
+ size 20541173898
checkpoint-500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b79ce956d0906cb3482b1d52bcd15b5b8647283775e67bd74da0beeb7a344da
3
+ size 14408
checkpoint-500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18b984273ea2d45b7ffb1d047bb359d93111e41fcad70d16a1b453fd38f72636
3
+ size 988
checkpoint-500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c19de7558b70194a5db023dd9d9ec6692e8d0297ac9e51abe4c74da457138fb
3
+ size 1000
checkpoint-500/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.31.0.dev0",
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
+ }
checkpoint-500/unet/diffusion_pytorch_model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42f62b1fcbd20117b945a8d8206efd5a1984e5c087210e12c34650e5ce2122ac
3
+ size 9988139160
checkpoint-500/unet/diffusion_pytorch_model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1263c730c1f4bd055a6a9e2cf98cd2f0dd18f615e60b8c615767701e1568654b
3
+ size 281938304
checkpoint-500/unet/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/unet_ema/config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.31.0.dev0",
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
+ "decay": 0.9999,
28
+ "down_block_types": [
29
+ "DownBlock2D",
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D"
32
+ ],
33
+ "downsample_padding": 1,
34
+ "dropout": 0.0,
35
+ "dual_cross_attention": false,
36
+ "encoder_hid_dim": null,
37
+ "encoder_hid_dim_type": null,
38
+ "flip_sin_to_cos": true,
39
+ "freq_shift": 0,
40
+ "in_channels": 4,
41
+ "inv_gamma": 1.0,
42
+ "layers_per_block": 2,
43
+ "mid_block_only_cross_attention": null,
44
+ "mid_block_scale_factor": 1,
45
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
46
+ "min_decay": 0.0,
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
+ "optimization_step": 500,
53
+ "out_channels": 4,
54
+ "power": 0.6666666666666666,
55
+ "projection_class_embeddings_input_dim": 2816,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "reverse_transformer_layers_per_block": null,
60
+ "sample_size": 128,
61
+ "time_cond_proj_dim": null,
62
+ "time_embedding_act_fn": null,
63
+ "time_embedding_dim": null,
64
+ "time_embedding_type": "positional",
65
+ "timestep_post_act": null,
66
+ "transformer_layers_per_block": [
67
+ 1,
68
+ 2,
69
+ 10
70
+ ],
71
+ "up_block_types": [
72
+ "CrossAttnUpBlock2D",
73
+ "CrossAttnUpBlock2D",
74
+ "UpBlock2D"
75
+ ],
76
+ "upcast_attention": null,
77
+ "update_after_step": 0,
78
+ "use_ema_warmup": false,
79
+ "use_linear_projection": true
80
+ }
checkpoint-500/unet_ema/diffusion_pytorch_model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd7c0d50cd7559130044dfb922b3f776cf82b7d861106ad04ff8821e127c260f
3
+ size 9988139160
checkpoint-500/unet_ema/diffusion_pytorch_model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f4dd87231c8646ae5c7ddb071dc0c3f3e5defae5f746005458f1b8ea40cbc03
3
+ size 281938304
checkpoint-500/unet_ema/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
image_0.png ADDED