Hugging Face's logo

Zaid
/
sd-text-english

Text-to-Image
Diffusers
TensorBoard
StableDiffusionPipeline
Inference Endpoints
Model card Files Metrics Community
Zaid commited on
Commit
bf68daa
·
1 Parent(s): 9399006

End of training

Browse files
Files changed (38) hide show
  1. .gitignore +2 -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 +51 -0
  7. checkpoint-1000/unet/diffusion_pytorch_model.bin +3 -0
  8. checkpoint-1000/unet_ema/config.json +58 -0
  9. checkpoint-1000/unet_ema/diffusion_pytorch_model.bin +3 -0
  10. checkpoint-500/optimizer.bin +3 -0
  11. checkpoint-500/random_states_0.pkl +3 -0
  12. checkpoint-500/scaler.pt +3 -0
  13. checkpoint-500/scheduler.bin +3 -0
  14. checkpoint-500/unet/config.json +51 -0
  15. checkpoint-500/unet/diffusion_pytorch_model.bin +3 -0
  16. checkpoint-500/unet_ema/config.json +58 -0
  17. checkpoint-500/unet_ema/diffusion_pytorch_model.bin +3 -0
  18. feature_extractor/preprocessor_config.json +28 -0
  19. logs/text2image-fine-tune/1677268358.5017004/events.out.tfevents.1677268358.7ca78f72610a.1275.1 +3 -0
  20. logs/text2image-fine-tune/1677268358.5032947/hparams.yml +44 -0
  21. logs/text2image-fine-tune/1677268453.7739494/events.out.tfevents.1677268453.7ca78f72610a.1934.1 +3 -0
  22. logs/text2image-fine-tune/1677268453.7755494/hparams.yml +44 -0
  23. logs/text2image-fine-tune/events.out.tfevents.1677268358.7ca78f72610a.1275.0 +3 -0
  24. logs/text2image-fine-tune/events.out.tfevents.1677268453.7ca78f72610a.1934.0 +3 -0
  25. model_index.json +33 -0
  26. safety_checker/config.json +181 -0
  27. safety_checker/pytorch_model.bin +3 -0
  28. scheduler/scheduler_config.json +14 -0
  29. text_encoder/config.json +25 -0
  30. text_encoder/pytorch_model.bin +3 -0
  31. tokenizer/merges.txt +0 -0
  32. tokenizer/special_tokens_map.json +24 -0
  33. tokenizer/tokenizer_config.json +34 -0
  34. tokenizer/vocab.json +0 -0
  35. unet/config.json +51 -0
  36. unet/diffusion_pytorch_model.bin +3 -0
  37. vae/config.json +31 -0
  38. vae/diffusion_pytorch_model.bin +3 -0
.gitignore ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ step_*
2
+ epoch_*
checkpoint-1000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9db0b67fb4b0728ef44d956ddaed27f8c4bc1833a15f8d63063f1422ebda0496
3
+ size 6876749339
checkpoint-1000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff9ae30a9cc56676a46bcd4270541a293618c3c5b4835c1bd4ee087b7c5481c4
3
+ size 14727
checkpoint-1000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68cff80b680ddf6e7abbef98b5f336b97f9b5963e2209307f639383870e8cc71
3
+ size 557
checkpoint-1000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f34912fa092355c5a950e4967ea28cbb3556238a7857baa5999d228cde0ae4c3
3
+ size 563
checkpoint-1000/unet/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.14.0.dev0",
4
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": 8,
7
+ "block_out_channels": [
8
+ 320,
9
+ 640,
10
+ 1280,
11
+ 1280
12
+ ],
13
+ "center_input_sample": false,
14
+ "class_embed_type": null,
15
+ "conv_in_kernel": 3,
16
+ "conv_out_kernel": 3,
17
+ "cross_attention_dim": 768,
18
+ "down_block_types": [
19
+ "CrossAttnDownBlock2D",
20
+ "CrossAttnDownBlock2D",
21
+ "CrossAttnDownBlock2D",
22
+ "DownBlock2D"
23
+ ],
24
+ "downsample_padding": 1,
25
+ "dual_cross_attention": false,
26
+ "flip_sin_to_cos": true,
27
+ "freq_shift": 0,
28
+ "in_channels": 4,
29
+ "layers_per_block": 2,
30
+ "mid_block_scale_factor": 1,
31
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
32
+ "norm_eps": 1e-05,
33
+ "norm_num_groups": 32,
34
+ "num_class_embeds": null,
35
+ "only_cross_attention": false,
36
+ "out_channels": 4,
37
+ "projection_class_embeddings_input_dim": null,
38
+ "resnet_time_scale_shift": "default",
39
+ "sample_size": 64,
40
+ "time_cond_proj_dim": null,
41
+ "time_embedding_type": "positional",
42
+ "timestep_post_act": null,
43
+ "up_block_types": [
44
+ "UpBlock2D",
45
+ "CrossAttnUpBlock2D",
46
+ "CrossAttnUpBlock2D",
47
+ "CrossAttnUpBlock2D"
48
+ ],
49
+ "upcast_attention": false,
50
+ "use_linear_projection": false
51
+ }
checkpoint-1000/unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1d7b0dc8b17ea20d43d6822495aaab82f85068666214a3371d6a3097066289c
3
+ size 3438375973
checkpoint-1000/unet_ema/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.14.0.dev0",
4
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": 8,
7
+ "block_out_channels": [
8
+ 320,
9
+ 640,
10
+ 1280,
11
+ 1280
12
+ ],
13
+ "center_input_sample": false,
14
+ "class_embed_type": null,
15
+ "conv_in_kernel": 3,
16
+ "conv_out_kernel": 3,
17
+ "cross_attention_dim": 768,
18
+ "decay": 0.9999,
19
+ "down_block_types": [
20
+ "CrossAttnDownBlock2D",
21
+ "CrossAttnDownBlock2D",
22
+ "CrossAttnDownBlock2D",
23
+ "DownBlock2D"
24
+ ],
25
+ "downsample_padding": 1,
26
+ "dual_cross_attention": false,
27
+ "flip_sin_to_cos": true,
28
+ "freq_shift": 0,
29
+ "in_channels": 4,
30
+ "inv_gamma": 1.0,
31
+ "layers_per_block": 2,
32
+ "mid_block_scale_factor": 1,
33
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
34
+ "min_decay": 0.0,
35
+ "norm_eps": 1e-05,
36
+ "norm_num_groups": 32,
37
+ "num_class_embeds": null,
38
+ "only_cross_attention": false,
39
+ "optimization_step": 1000,
40
+ "out_channels": 4,
41
+ "power": 0.6666666666666666,
42
+ "projection_class_embeddings_input_dim": null,
43
+ "resnet_time_scale_shift": "default",
44
+ "sample_size": 64,
45
+ "time_cond_proj_dim": null,
46
+ "time_embedding_type": "positional",
47
+ "timestep_post_act": null,
48
+ "up_block_types": [
49
+ "UpBlock2D",
50
+ "CrossAttnUpBlock2D",
51
+ "CrossAttnUpBlock2D",
52
+ "CrossAttnUpBlock2D"
53
+ ],
54
+ "upcast_attention": false,
55
+ "update_after_step": 0,
56
+ "use_ema_warmup": false,
57
+ "use_linear_projection": false
58
+ }
checkpoint-1000/unet_ema/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa1aad9d3a8f107f88b3699536938f6d80de6726cd62120c9012ed763ca387f1
3
+ size 3438366373
checkpoint-500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c12d22ddbe1a3b68577f0279ee0e054c1941ae848ba8b01fd7fe6cbb4f279c28
3
+ size 6876749339
checkpoint-500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c67c977515b3b803922745da13ff6768545b630b66aee61dde0bdd33b0959ad6
3
+ size 14727
checkpoint-500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3f196a54202bb4ba1220e8c59f42f9cda0702d68ea83147d814c2fb2f36b8f2
3
+ size 557
checkpoint-500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab20ead000e6ae60e9a32d69fb1fb976d10dba2a065da680293a8202053a1975
3
+ size 563
checkpoint-500/unet/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.14.0.dev0",
4
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": 8,
7
+ "block_out_channels": [
8
+ 320,
9
+ 640,
10
+ 1280,
11
+ 1280
12
+ ],
13
+ "center_input_sample": false,
14
+ "class_embed_type": null,
15
+ "conv_in_kernel": 3,
16
+ "conv_out_kernel": 3,
17
+ "cross_attention_dim": 768,
18
+ "down_block_types": [
19
+ "CrossAttnDownBlock2D",
20
+ "CrossAttnDownBlock2D",
21
+ "CrossAttnDownBlock2D",
22
+ "DownBlock2D"
23
+ ],
24
+ "downsample_padding": 1,
25
+ "dual_cross_attention": false,
26
+ "flip_sin_to_cos": true,
27
+ "freq_shift": 0,
28
+ "in_channels": 4,
29
+ "layers_per_block": 2,
30
+ "mid_block_scale_factor": 1,
31
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
32
+ "norm_eps": 1e-05,
33
+ "norm_num_groups": 32,
34
+ "num_class_embeds": null,
35
+ "only_cross_attention": false,
36
+ "out_channels": 4,
37
+ "projection_class_embeddings_input_dim": null,
38
+ "resnet_time_scale_shift": "default",
39
+ "sample_size": 64,
40
+ "time_cond_proj_dim": null,
41
+ "time_embedding_type": "positional",
42
+ "timestep_post_act": null,
43
+ "up_block_types": [
44
+ "UpBlock2D",
45
+ "CrossAttnUpBlock2D",
46
+ "CrossAttnUpBlock2D",
47
+ "CrossAttnUpBlock2D"
48
+ ],
49
+ "upcast_attention": false,
50
+ "use_linear_projection": false
51
+ }
checkpoint-500/unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2cb69d4d27912b05fdb088a7e760581fedc7a03e41b0c63a3f633822f9c01d3
3
+ size 3438375973
checkpoint-500/unet_ema/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.14.0.dev0",
4
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": 8,
7
+ "block_out_channels": [
8
+ 320,
9
+ 640,
10
+ 1280,
11
+ 1280
12
+ ],
13
+ "center_input_sample": false,
14
+ "class_embed_type": null,
15
+ "conv_in_kernel": 3,
16
+ "conv_out_kernel": 3,
17
+ "cross_attention_dim": 768,
18
+ "decay": 0.9999,
19
+ "down_block_types": [
20
+ "CrossAttnDownBlock2D",
21
+ "CrossAttnDownBlock2D",
22
+ "CrossAttnDownBlock2D",
23
+ "DownBlock2D"
24
+ ],
25
+ "downsample_padding": 1,
26
+ "dual_cross_attention": false,
27
+ "flip_sin_to_cos": true,
28
+ "freq_shift": 0,
29
+ "in_channels": 4,
30
+ "inv_gamma": 1.0,
31
+ "layers_per_block": 2,
32
+ "mid_block_scale_factor": 1,
33
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
34
+ "min_decay": 0.0,
35
+ "norm_eps": 1e-05,
36
+ "norm_num_groups": 32,
37
+ "num_class_embeds": null,
38
+ "only_cross_attention": false,
39
+ "optimization_step": 500,
40
+ "out_channels": 4,
41
+ "power": 0.6666666666666666,
42
+ "projection_class_embeddings_input_dim": null,
43
+ "resnet_time_scale_shift": "default",
44
+ "sample_size": 64,
45
+ "time_cond_proj_dim": null,
46
+ "time_embedding_type": "positional",
47
+ "timestep_post_act": null,
48
+ "up_block_types": [
49
+ "UpBlock2D",
50
+ "CrossAttnUpBlock2D",
51
+ "CrossAttnUpBlock2D",
52
+ "CrossAttnUpBlock2D"
53
+ ],
54
+ "upcast_attention": false,
55
+ "update_after_step": 0,
56
+ "use_ema_warmup": false,
57
+ "use_linear_projection": false
58
+ }
checkpoint-500/unet_ema/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6702ed02a6e9b80ac997526deb29db9aae322c7e8a8d8d8675b82ed1d126b400
3
+ size 3438366373
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "feature_extractor_type": "CLIPFeatureExtractor",
12
+ "image_mean": [
13
+ 0.48145466,
14
+ 0.4578275,
15
+ 0.40821073
16
+ ],
17
+ "image_processor_type": "CLIPFeatureExtractor",
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "shortest_edge": 224
27
+ }
28
+ }
logs/text2image-fine-tune/1677268358.5017004/events.out.tfevents.1677268358.7ca78f72610a.1275.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b23d68426f93a5dc779b86451fad35728c463490dc25eb0a37a77121f260244
3
+ size 1918
logs/text2image-fine-tune/1677268358.5032947/hparams.yml ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: arbml/FontsSmall
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 8
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ learning_rate: 1.0e-05
21
+ local_rank: -1
22
+ logging_dir: logs
23
+ lr_scheduler: constant
24
+ lr_warmup_steps: 0
25
+ max_grad_norm: 1.0
26
+ max_train_samples: null
27
+ max_train_steps: 15000
28
+ mixed_precision: null
29
+ non_ema_revision: null
30
+ num_train_epochs: 120
31
+ output_dir: sd-text-english
32
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
33
+ push_to_hub: true
34
+ random_flip: true
35
+ report_to: tensorboard
36
+ resolution: 512
37
+ resume_from_checkpoint: null
38
+ revision: null
39
+ scale_lr: false
40
+ seed: null
41
+ train_batch_size: 1
42
+ train_data_dir: null
43
+ use_8bit_adam: false
44
+ use_ema: true
logs/text2image-fine-tune/1677268453.7739494/events.out.tfevents.1677268453.7ca78f72610a.1934.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2365dddfa7fce91947c9f1f5a6d023dc4bf96aef8186852ce0b1fd3b78e6ddd
3
+ size 1918
logs/text2image-fine-tune/1677268453.7755494/hparams.yml ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: arbml/FontsSmall
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 8
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ learning_rate: 1.0e-05
21
+ local_rank: -1
22
+ logging_dir: logs
23
+ lr_scheduler: constant
24
+ lr_warmup_steps: 0
25
+ max_grad_norm: 1.0
26
+ max_train_samples: null
27
+ max_train_steps: 1000
28
+ mixed_precision: null
29
+ non_ema_revision: null
30
+ num_train_epochs: 8
31
+ output_dir: sd-text-english
32
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
33
+ push_to_hub: true
34
+ random_flip: true
35
+ report_to: tensorboard
36
+ resolution: 512
37
+ resume_from_checkpoint: null
38
+ revision: null
39
+ scale_lr: false
40
+ seed: null
41
+ train_batch_size: 1
42
+ train_data_dir: null
43
+ use_8bit_adam: false
44
+ use_ema: true
logs/text2image-fine-tune/events.out.tfevents.1677268358.7ca78f72610a.1275.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9701e60a9814fffee55b53a14694ae2c9720dbb3734e271787b71e15596c7a6f
3
+ size 856
logs/text2image-fine-tune/events.out.tfevents.1677268453.7ca78f72610a.1934.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02911b19411d9ad1d8595506669e22002e27364d9ccb88c392422f6dda7d0aa7
3
+ size 48913
model_index.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.14.0.dev0",
4
+ "feature_extractor": [
5
+ "transformers",
6
+ "CLIPFeatureExtractor"
7
+ ],
8
+ "requires_safety_checker": true,
9
+ "safety_checker": [
10
+ "stable_diffusion",
11
+ "StableDiffusionSafetyChecker"
12
+ ],
13
+ "scheduler": [
14
+ "diffusers",
15
+ "PNDMScheduler"
16
+ ],
17
+ "text_encoder": [
18
+ "transformers",
19
+ "CLIPTextModel"
20
+ ],
21
+ "tokenizer": [
22
+ "transformers",
23
+ "CLIPTokenizer"
24
+ ],
25
+ "unet": [
26
+ "diffusers",
27
+ "UNet2DConditionModel"
28
+ ],
29
+ "vae": [
30
+ "diffusers",
31
+ "AutoencoderKL"
32
+ ]
33
+ }
safety_checker/config.json ADDED
@@ -0,0 +1,181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "3857c45b7d4e78b3ba0f39d4d7f50a2a05aa23d4",
3
+ "_name_or_path": "/root/.cache/huggingface/diffusers/models--CompVis--stable-diffusion-v1-4/snapshots/3857c45b7d4e78b3ba0f39d4d7f50a2a05aa23d4/safety_checker",
4
+ "architectures": [
5
+ "StableDiffusionSafetyChecker"
6
+ ],
7
+ "initializer_factor": 1.0,
8
+ "logit_scale_init_value": 2.6592,
9
+ "model_type": "clip",
10
+ "projection_dim": 768,
11
+ "text_config": {
12
+ "_name_or_path": "",
13
+ "add_cross_attention": false,
14
+ "architectures": null,
15
+ "attention_dropout": 0.0,
16
+ "bad_words_ids": null,
17
+ "begin_suppress_tokens": null,
18
+ "bos_token_id": 0,
19
+ "chunk_size_feed_forward": 0,
20
+ "cross_attention_hidden_size": null,
21
+ "decoder_start_token_id": null,
22
+ "diversity_penalty": 0.0,
23
+ "do_sample": false,
24
+ "dropout": 0.0,
25
+ "early_stopping": false,
26
+ "encoder_no_repeat_ngram_size": 0,
27
+ "eos_token_id": 2,
28
+ "exponential_decay_length_penalty": null,
29
+ "finetuning_task": null,
30
+ "forced_bos_token_id": null,
31
+ "forced_eos_token_id": null,
32
+ "hidden_act": "quick_gelu",
33
+ "hidden_size": 768,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1"
37
+ },
38
+ "initializer_factor": 1.0,
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 3072,
41
+ "is_decoder": false,
42
+ "is_encoder_decoder": false,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1
46
+ },
47
+ "layer_norm_eps": 1e-05,
48
+ "length_penalty": 1.0,
49
+ "max_length": 20,
50
+ "max_position_embeddings": 77,
51
+ "min_length": 0,
52
+ "model_type": "clip_text_model",
53
+ "no_repeat_ngram_size": 0,
54
+ "num_attention_heads": 12,
55
+ "num_beam_groups": 1,
56
+ "num_beams": 1,
57
+ "num_hidden_layers": 12,
58
+ "num_return_sequences": 1,
59
+ "output_attentions": false,
60
+ "output_hidden_states": false,
61
+ "output_scores": false,
62
+ "pad_token_id": 1,
63
+ "prefix": null,
64
+ "problem_type": null,
65
+ "projection_dim": 512,
66
+ "pruned_heads": {},
67
+ "remove_invalid_values": false,
68
+ "repetition_penalty": 1.0,
69
+ "return_dict": true,
70
+ "return_dict_in_generate": false,
71
+ "sep_token_id": null,
72
+ "suppress_tokens": null,
73
+ "task_specific_params": null,
74
+ "temperature": 1.0,
75
+ "tf_legacy_loss": false,
76
+ "tie_encoder_decoder": false,
77
+ "tie_word_embeddings": true,
78
+ "tokenizer_class": null,
79
+ "top_k": 50,
80
+ "top_p": 1.0,
81
+ "torch_dtype": null,
82
+ "torchscript": false,
83
+ "transformers_version": "4.26.1",
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "vocab_size": 49408
87
+ },
88
+ "text_config_dict": {
89
+ "hidden_size": 768,
90
+ "intermediate_size": 3072,
91
+ "num_attention_heads": 12,
92
+ "num_hidden_layers": 12
93
+ },
94
+ "torch_dtype": "float32",
95
+ "transformers_version": null,
96
+ "vision_config": {
97
+ "_name_or_path": "",
98
+ "add_cross_attention": false,
99
+ "architectures": null,
100
+ "attention_dropout": 0.0,
101
+ "bad_words_ids": null,
102
+ "begin_suppress_tokens": null,
103
+ "bos_token_id": null,
104
+ "chunk_size_feed_forward": 0,
105
+ "cross_attention_hidden_size": null,
106
+ "decoder_start_token_id": null,
107
+ "diversity_penalty": 0.0,
108
+ "do_sample": false,
109
+ "dropout": 0.0,
110
+ "early_stopping": false,
111
+ "encoder_no_repeat_ngram_size": 0,
112
+ "eos_token_id": null,
113
+ "exponential_decay_length_penalty": null,
114
+ "finetuning_task": null,
115
+ "forced_bos_token_id": null,
116
+ "forced_eos_token_id": null,
117
+ "hidden_act": "quick_gelu",
118
+ "hidden_size": 1024,
119
+ "id2label": {
120
+ "0": "LABEL_0",
121
+ "1": "LABEL_1"
122
+ },
123
+ "image_size": 224,
124
+ "initializer_factor": 1.0,
125
+ "initializer_range": 0.02,
126
+ "intermediate_size": 4096,
127
+ "is_decoder": false,
128
+ "is_encoder_decoder": false,
129
+ "label2id": {
130
+ "LABEL_0": 0,
131
+ "LABEL_1": 1
132
+ },
133
+ "layer_norm_eps": 1e-05,
134
+ "length_penalty": 1.0,
135
+ "max_length": 20,
136
+ "min_length": 0,
137
+ "model_type": "clip_vision_model",
138
+ "no_repeat_ngram_size": 0,
139
+ "num_attention_heads": 16,
140
+ "num_beam_groups": 1,
141
+ "num_beams": 1,
142
+ "num_channels": 3,
143
+ "num_hidden_layers": 24,
144
+ "num_return_sequences": 1,
145
+ "output_attentions": false,
146
+ "output_hidden_states": false,
147
+ "output_scores": false,
148
+ "pad_token_id": null,
149
+ "patch_size": 14,
150
+ "prefix": null,
151
+ "problem_type": null,
152
+ "projection_dim": 512,
153
+ "pruned_heads": {},
154
+ "remove_invalid_values": false,
155
+ "repetition_penalty": 1.0,
156
+ "return_dict": true,
157
+ "return_dict_in_generate": false,
158
+ "sep_token_id": null,
159
+ "suppress_tokens": null,
160
+ "task_specific_params": null,
161
+ "temperature": 1.0,
162
+ "tf_legacy_loss": false,
163
+ "tie_encoder_decoder": false,
164
+ "tie_word_embeddings": true,
165
+ "tokenizer_class": null,
166
+ "top_k": 50,
167
+ "top_p": 1.0,
168
+ "torch_dtype": null,
169
+ "torchscript": false,
170
+ "transformers_version": "4.26.1",
171
+ "typical_p": 1.0,
172
+ "use_bfloat16": false
173
+ },
174
+ "vision_config_dict": {
175
+ "hidden_size": 1024,
176
+ "intermediate_size": 4096,
177
+ "num_attention_heads": 16,
178
+ "num_hidden_layers": 24,
179
+ "patch_size": 14
180
+ }
181
+ }
safety_checker/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
3
+ size 1216064769
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.14.0.dev0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "num_train_timesteps": 1000,
9
+ "prediction_type": "epsilon",
10
+ "set_alpha_to_one": false,
11
+ "skip_prk_steps": true,
12
+ "steps_offset": 1,
13
+ "trained_betas": null
14
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
3
+ "architectures": [
4
+ "CLIPTextModel"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dropout": 0.0,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "quick_gelu",
11
+ "hidden_size": 768,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 512,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.26.1",
24
+ "vocab_size": 49408
25
+ }
text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a34f30098988d85dc0fb0fc272a842ebcf552e2ebc6ce4adbcf3695d08e8a90
3
+ size 246188833
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "do_lower_case": true,
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 77,
22
+ "name_or_path": "/root/.cache/huggingface/diffusers/models--CompVis--stable-diffusion-v1-4/snapshots/3857c45b7d4e78b3ba0f39d4d7f50a2a05aa23d4/tokenizer",
23
+ "pad_token": "<|endoftext|>",
24
+ "special_tokens_map_file": "./special_tokens_map.json",
25
+ "tokenizer_class": "CLIPTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.14.0.dev0",
4
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": 8,
7
+ "block_out_channels": [
8
+ 320,
9
+ 640,
10
+ 1280,
11
+ 1280
12
+ ],
13
+ "center_input_sample": false,
14
+ "class_embed_type": null,
15
+ "conv_in_kernel": 3,
16
+ "conv_out_kernel": 3,
17
+ "cross_attention_dim": 768,
18
+ "down_block_types": [
19
+ "CrossAttnDownBlock2D",
20
+ "CrossAttnDownBlock2D",
21
+ "CrossAttnDownBlock2D",
22
+ "DownBlock2D"
23
+ ],
24
+ "downsample_padding": 1,
25
+ "dual_cross_attention": false,
26
+ "flip_sin_to_cos": true,
27
+ "freq_shift": 0,
28
+ "in_channels": 4,
29
+ "layers_per_block": 2,
30
+ "mid_block_scale_factor": 1,
31
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
32
+ "norm_eps": 1e-05,
33
+ "norm_num_groups": 32,
34
+ "num_class_embeds": null,
35
+ "only_cross_attention": false,
36
+ "out_channels": 4,
37
+ "projection_class_embeddings_input_dim": null,
38
+ "resnet_time_scale_shift": "default",
39
+ "sample_size": 64,
40
+ "time_cond_proj_dim": null,
41
+ "time_embedding_type": "positional",
42
+ "timestep_post_act": null,
43
+ "up_block_types": [
44
+ "UpBlock2D",
45
+ "CrossAttnUpBlock2D",
46
+ "CrossAttnUpBlock2D",
47
+ "CrossAttnUpBlock2D"
48
+ ],
49
+ "upcast_attention": false,
50
+ "use_linear_projection": false
51
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de53f01e8be5f88fd1e992a02fee34fcc8e8f0acb67685569528705b881ebce0
3
+ size 3438375973
vae/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.14.0.dev0",
4
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "down_block_types": [
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D"
17
+ ],
18
+ "in_channels": 3,
19
+ "latent_channels": 4,
20
+ "layers_per_block": 2,
21
+ "norm_num_groups": 32,
22
+ "out_channels": 3,
23
+ "sample_size": 512,
24
+ "scaling_factor": 0.18215,
25
+ "up_block_types": [
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D"
30
+ ]
31
+ }
vae/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3524731ccb7c457ec5481e252c774463677e51ef4df7fccb6f88534b632acf92
3
+ size 167407601