Hugging Face's logo

c-eshih
/
instruct-pix2pix-model

Diffusers
TensorBoard
Safetensors
StableDiffusionInstructPix2PixPipeline
Model card Files Metrics Community
c-eshih commited on
Commit
b51f059
•
1 Parent(s): 1df10b6

End of training

Browse files
Files changed (33) hide show
  1. checkpoint-15000/optimizer.bin +3 -0
  2. checkpoint-15000/random_states_0.pkl +3 -0
  3. checkpoint-15000/scaler.pt +3 -0
  4. checkpoint-15000/scheduler.bin +3 -0
  5. checkpoint-15000/unet/config.json +68 -0
  6. checkpoint-15000/unet/diffusion_pytorch_model.safetensors +3 -0
  7. feature_extractor/preprocessor_config.json +44 -0
  8. logs/instruct-pix2pix/1718315898.8147628/events.out.tfevents.1718315898.ambus-algoq6069.252288.1 +3 -0
  9. logs/instruct-pix2pix/1718315898.8174675/hparams.yml +51 -0
  10. logs/instruct-pix2pix/1718316105.346568/events.out.tfevents.1718316105.ambus-algoq6069.253667.1 +3 -0
  11. logs/instruct-pix2pix/1718316105.34985/hparams.yml +51 -0
  12. logs/instruct-pix2pix/1718316198.50107/events.out.tfevents.1718316198.ambus-algoq6069.254430.1 +3 -0
  13. logs/instruct-pix2pix/1718316198.5046031/hparams.yml +51 -0
  14. logs/instruct-pix2pix/1718330036.5076668/events.out.tfevents.1718330036.ambus-algoq6069.336921.1 +3 -0
  15. logs/instruct-pix2pix/1718330036.5114558/hparams.yml +51 -0
  16. logs/instruct-pix2pix/events.out.tfevents.1718315898.ambus-algoq6069.252288.0 +3 -0
  17. logs/instruct-pix2pix/events.out.tfevents.1718316105.ambus-algoq6069.253667.0 +3 -0
  18. logs/instruct-pix2pix/events.out.tfevents.1718316198.ambus-algoq6069.254430.0 +3 -0
  19. logs/instruct-pix2pix/events.out.tfevents.1718330036.ambus-algoq6069.336921.0 +3 -0
  20. model_index.json +38 -0
  21. safety_checker/config.json +28 -0
  22. safety_checker/model.safetensors +3 -0
  23. scheduler/scheduler_config.json +15 -0
  24. text_encoder/config.json +25 -0
  25. text_encoder/model.safetensors +3 -0
  26. tokenizer/merges.txt +0 -0
  27. tokenizer/special_tokens_map.json +24 -0
  28. tokenizer/tokenizer_config.json +30 -0
  29. tokenizer/vocab.json +0 -0
  30. unet/config.json +68 -0
  31. unet/diffusion_pytorch_model.safetensors +3 -0
  32. vae/config.json +34 -0
  33. vae/diffusion_pytorch_model.safetensors +3 -0
checkpoint-15000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:530c3e03a97406f4743bbcd7cc9879882328b4113cd653f393a20d9853fcc5c3
3
+ size 6876851924
checkpoint-15000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e4dde60b2e5183914c844c77e5631918a531110d9db3038e9b3d1e019459780
3
+ size 15124
checkpoint-15000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eecddb7ae6cfe0e1faf06996b98aefc71b120ef9e1e738bf94e78482420a7e05
3
+ size 988
checkpoint-15000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4b6fed06972ca6d8f84975e458de6d9d6e977ceb58cb9472f69fec51c80e6ee
3
+ size 1000
checkpoint-15000/unet/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.29.0.dev0",
4
+ "_name_or_path": "instruct-pix2pix-model/checkpoint-5000",
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": 8,
10
+ "attention_type": "default",
11
+ "block_out_channels": [
12
+ 320,
13
+ 640,
14
+ 1280,
15
+ 1280
16
+ ],
17
+ "center_input_sample": false,
18
+ "class_embed_type": null,
19
+ "class_embeddings_concat": false,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 768,
23
+ "cross_attention_norm": null,
24
+ "down_block_types": [
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "DownBlock2D"
29
+ ],
30
+ "downsample_padding": 1,
31
+ "dropout": 0.0,
32
+ "dual_cross_attention": false,
33
+ "encoder_hid_dim": null,
34
+ "encoder_hid_dim_type": null,
35
+ "flip_sin_to_cos": true,
36
+ "freq_shift": 0,
37
+ "in_channels": 8,
38
+ "layers_per_block": 2,
39
+ "mid_block_only_cross_attention": null,
40
+ "mid_block_scale_factor": 1,
41
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
42
+ "norm_eps": 1e-05,
43
+ "norm_num_groups": 32,
44
+ "num_attention_heads": null,
45
+ "num_class_embeds": null,
46
+ "only_cross_attention": false,
47
+ "out_channels": 4,
48
+ "projection_class_embeddings_input_dim": null,
49
+ "resnet_out_scale_factor": 1.0,
50
+ "resnet_skip_time_act": false,
51
+ "resnet_time_scale_shift": "default",
52
+ "reverse_transformer_layers_per_block": null,
53
+ "sample_size": 64,
54
+ "time_cond_proj_dim": null,
55
+ "time_embedding_act_fn": null,
56
+ "time_embedding_dim": null,
57
+ "time_embedding_type": "positional",
58
+ "timestep_post_act": null,
59
+ "transformer_layers_per_block": 1,
60
+ "up_block_types": [
61
+ "UpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D",
64
+ "CrossAttnUpBlock2D"
65
+ ],
66
+ "upcast_attention": false,
67
+ "use_linear_projection": false
68
+ }
checkpoint-15000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:433d3b03fe63d0ed58b132be188665ff9eae37e37d32eb050fe58791f282fb16
3
+ size 3438213624
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "do_center_crop",
8
+ "crop_size",
9
+ "do_rescale",
10
+ "rescale_factor",
11
+ "do_normalize",
12
+ "image_mean",
13
+ "image_std",
14
+ "do_convert_rgb",
15
+ "return_tensors",
16
+ "data_format",
17
+ "input_data_format"
18
+ ],
19
+ "crop_size": {
20
+ "height": 224,
21
+ "width": 224
22
+ },
23
+ "do_center_crop": true,
24
+ "do_convert_rgb": true,
25
+ "do_normalize": true,
26
+ "do_rescale": true,
27
+ "do_resize": true,
28
+ "image_mean": [
29
+ 0.48145466,
30
+ 0.4578275,
31
+ 0.40821073
32
+ ],
33
+ "image_processor_type": "CLIPImageProcessor",
34
+ "image_std": [
35
+ 0.26862954,
36
+ 0.26130258,
37
+ 0.27577711
38
+ ],
39
+ "resample": 3,
40
+ "rescale_factor": 0.00392156862745098,
41
+ "size": {
42
+ "shortest_edge": 224
43
+ }
44
+ }
logs/instruct-pix2pix/1718315898.8147628/events.out.tfevents.1718315898.ambus-algoq6069.252288.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43d444606091f838dfe98b4a403ef2f5c1c0e4fd77cc06957e0f138793e0953e
3
+ size 2429
logs/instruct-pix2pix/1718315898.8174675/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: fusing/instructpix2pix-1000-samples
14
+ edit_prompt_column: edit_prompt
15
+ edited_image_column: edited_image
16
+ enable_xformers_memory_efficient_attention: true
17
+ gradient_accumulation_steps: 4
18
+ gradient_checkpointing: true
19
+ hub_model_id: null
20
+ hub_token: null
21
+ learning_rate: 5.0e-05
22
+ local_rank: 0
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 15000
29
+ mixed_precision: fp16
30
+ non_ema_revision: null
31
+ num_train_epochs: 938
32
+ num_validation_images: 4
33
+ original_image_column: input_image
34
+ output_dir: instruct-pix2pix-model
35
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 256
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
44
+ train_batch_size: 4
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: false
48
+ val_image_url: null
49
+ validation_epochs: 1
50
+ validation_prompt: null
51
+ variant: null
logs/instruct-pix2pix/1718316105.346568/events.out.tfevents.1718316105.ambus-algoq6069.253667.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6993821ae4ba9ca51d8aee5533b91617439abc3a1a0433340d6fd7c3c682b24d
3
+ size 2429
logs/instruct-pix2pix/1718316105.34985/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: fusing/instructpix2pix-1000-samples
14
+ edit_prompt_column: edit_prompt
15
+ edited_image_column: edited_image
16
+ enable_xformers_memory_efficient_attention: true
17
+ gradient_accumulation_steps: 4
18
+ gradient_checkpointing: true
19
+ hub_model_id: null
20
+ hub_token: null
21
+ learning_rate: 5.0e-05
22
+ local_rank: 0
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 15000
29
+ mixed_precision: fp16
30
+ non_ema_revision: null
31
+ num_train_epochs: 938
32
+ num_validation_images: 4
33
+ original_image_column: input_image
34
+ output_dir: instruct-pix2pix-model
35
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 256
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
44
+ train_batch_size: 4
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: false
48
+ val_image_url: null
49
+ validation_epochs: 1
50
+ validation_prompt: null
51
+ variant: null
logs/instruct-pix2pix/1718316198.50107/events.out.tfevents.1718316198.ambus-algoq6069.254430.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c800afe222cec16e60c2c3badec51d7b8be44c294b558c9f5ace40f14bbe150a
3
+ size 2429
logs/instruct-pix2pix/1718316198.5046031/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: fusing/instructpix2pix-1000-samples
14
+ edit_prompt_column: edit_prompt
15
+ edited_image_column: edited_image
16
+ enable_xformers_memory_efficient_attention: true
17
+ gradient_accumulation_steps: 4
18
+ gradient_checkpointing: true
19
+ hub_model_id: null
20
+ hub_token: null
21
+ learning_rate: 5.0e-05
22
+ local_rank: 0
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 15000
29
+ mixed_precision: fp16
30
+ non_ema_revision: null
31
+ num_train_epochs: 938
32
+ num_validation_images: 4
33
+ original_image_column: input_image
34
+ output_dir: instruct-pix2pix-model
35
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 256
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
44
+ train_batch_size: 4
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: false
48
+ val_image_url: null
49
+ validation_epochs: 1
50
+ validation_prompt: null
51
+ variant: null
logs/instruct-pix2pix/1718330036.5076668/events.out.tfevents.1718330036.ambus-algoq6069.336921.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f9ebfc2c2c7e3e22bc6f48d3867d88ac876d4c77b28f0a4e038a1df070492ce
3
+ size 2493
logs/instruct-pix2pix/1718330036.5114558/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ center_crop: false
8
+ checkpointing_steps: 100
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: fusing/instructpix2pix-1000-samples
14
+ edit_prompt_column: edit_prompt
15
+ edited_image_column: edited_image
16
+ enable_xformers_memory_efficient_attention: true
17
+ gradient_accumulation_steps: 4
18
+ gradient_checkpointing: true
19
+ hub_model_id: null
20
+ hub_token: null
21
+ learning_rate: 5.0e-05
22
+ local_rank: 0
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 15000
29
+ mixed_precision: fp16
30
+ non_ema_revision: null
31
+ num_train_epochs: 938
32
+ num_validation_images: 4
33
+ original_image_column: input_image
34
+ output_dir: instruct-pix2pix-model
35
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 256
40
+ resume_from_checkpoint: latest
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
44
+ train_batch_size: 4
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: false
48
+ val_image_url: null
49
+ validation_epochs: 1
50
+ validation_prompt: null
51
+ variant: null
logs/instruct-pix2pix/events.out.tfevents.1718315898.ambus-algoq6069.252288.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:899e8af918bc7caca0473bc6398e65c50898fe8baedb61a66ffccaa967625da1
3
+ size 3496
logs/instruct-pix2pix/events.out.tfevents.1718316105.ambus-algoq6069.253667.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7dff0e1034c0b694358d85704a22faea3507e48f8a7d3950f0f1de1e6ec9537
3
+ size 1000
logs/instruct-pix2pix/events.out.tfevents.1718316198.ambus-algoq6069.254430.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e79e58d8802b329730e512e27da2041eea79cd5221cd50c6708f368125ec163f
3
+ size 248636
logs/instruct-pix2pix/events.out.tfevents.1718330036.ambus-algoq6069.336921.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3254b07117745ca0daf3716f9243e193e9c1c2dd6ee01304de5e4c942282317a
3
+ size 490088
model_index.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionInstructPix2PixPipeline",
3
+ "_diffusers_version": "0.29.0.dev0",
4
+ "_name_or_path": "runwayml/stable-diffusion-v1-5",
5
+ "feature_extractor": [
6
+ "transformers",
7
+ "CLIPImageProcessor"
8
+ ],
9
+ "image_encoder": [
10
+ null,
11
+ null
12
+ ],
13
+ "requires_safety_checker": true,
14
+ "safety_checker": [
15
+ "stable_diffusion",
16
+ "StableDiffusionSafetyChecker"
17
+ ],
18
+ "scheduler": [
19
+ "diffusers",
20
+ "PNDMScheduler"
21
+ ],
22
+ "text_encoder": [
23
+ "transformers",
24
+ "CLIPTextModel"
25
+ ],
26
+ "tokenizer": [
27
+ "transformers",
28
+ "CLIPTokenizer"
29
+ ],
30
+ "unet": [
31
+ "diffusers",
32
+ "UNet2DConditionModel"
33
+ ],
34
+ "vae": [
35
+ "diffusers",
36
+ "AutoencoderKL"
37
+ ]
38
+ }
safety_checker/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/lhome1/c-eshih/.cache/hub/models--runwayml--stable-diffusion-v1-5/snapshots/1d0c4ebf6ff58a5caecab40fa1406526bca4b5b9/safety_checker",
3
+ "architectures": [
4
+ "StableDiffusionSafetyChecker"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "clip",
9
+ "projection_dim": 768,
10
+ "text_config": {
11
+ "dropout": 0.0,
12
+ "hidden_size": 768,
13
+ "intermediate_size": 3072,
14
+ "model_type": "clip_text_model",
15
+ "num_attention_heads": 12
16
+ },
17
+ "torch_dtype": "float32",
18
+ "transformers_version": "4.41.2",
19
+ "vision_config": {
20
+ "dropout": 0.0,
21
+ "hidden_size": 1024,
22
+ "intermediate_size": 4096,
23
+ "model_type": "clip_vision_model",
24
+ "num_attention_heads": 16,
25
+ "num_hidden_layers": 24,
26
+ "patch_size": 14
27
+ }
28
+ }
safety_checker/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
3
+ size 1215979664
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.29.0.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
+ "timestep_spacing": "leading",
14
+ "trained_betas": null
15
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "runwayml/stable-diffusion-v1-5",
3
+ "architectures": [
4
+ "CLIPTextModel"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dropout": 0.0,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "quick_gelu",
11
+ "hidden_size": 768,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 768,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.41.2",
24
+ "vocab_size": 49408
25
+ }
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
3
+ size 246144152
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 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "49406": {
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49407": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "bos_token": "<|startoftext|>",
22
+ "clean_up_tokenization_spaces": true,
23
+ "do_lower_case": true,
24
+ "eos_token": "<|endoftext|>",
25
+ "errors": "replace",
26
+ "model_max_length": 77,
27
+ "pad_token": "<|endoftext|>",
28
+ "tokenizer_class": "CLIPTokenizer",
29
+ "unk_token": "<|endoftext|>"
30
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.29.0.dev0",
4
+ "_name_or_path": "instruct-pix2pix-model/checkpoint-5000",
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": 8,
10
+ "attention_type": "default",
11
+ "block_out_channels": [
12
+ 320,
13
+ 640,
14
+ 1280,
15
+ 1280
16
+ ],
17
+ "center_input_sample": false,
18
+ "class_embed_type": null,
19
+ "class_embeddings_concat": false,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 768,
23
+ "cross_attention_norm": null,
24
+ "down_block_types": [
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "DownBlock2D"
29
+ ],
30
+ "downsample_padding": 1,
31
+ "dropout": 0.0,
32
+ "dual_cross_attention": false,
33
+ "encoder_hid_dim": null,
34
+ "encoder_hid_dim_type": null,
35
+ "flip_sin_to_cos": true,
36
+ "freq_shift": 0,
37
+ "in_channels": 8,
38
+ "layers_per_block": 2,
39
+ "mid_block_only_cross_attention": null,
40
+ "mid_block_scale_factor": 1,
41
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
42
+ "norm_eps": 1e-05,
43
+ "norm_num_groups": 32,
44
+ "num_attention_heads": null,
45
+ "num_class_embeds": null,
46
+ "only_cross_attention": false,
47
+ "out_channels": 4,
48
+ "projection_class_embeddings_input_dim": null,
49
+ "resnet_out_scale_factor": 1.0,
50
+ "resnet_skip_time_act": false,
51
+ "resnet_time_scale_shift": "default",
52
+ "reverse_transformer_layers_per_block": null,
53
+ "sample_size": 64,
54
+ "time_cond_proj_dim": null,
55
+ "time_embedding_act_fn": null,
56
+ "time_embedding_dim": null,
57
+ "time_embedding_type": "positional",
58
+ "timestep_post_act": null,
59
+ "transformer_layers_per_block": 1,
60
+ "up_block_types": [
61
+ "UpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D",
64
+ "CrossAttnUpBlock2D"
65
+ ],
66
+ "upcast_attention": false,
67
+ "use_linear_projection": false
68
+ }
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:433d3b03fe63d0ed58b132be188665ff9eae37e37d32eb050fe58791f282fb16
3
+ size 3438213624
vae/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.29.0.dev0",
4
+ "_name_or_path": "runwayml/stable-diffusion-v1-5",
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
+ "force_upcast": true,
19
+ "in_channels": 3,
20
+ "latent_channels": 4,
21
+ "latents_mean": null,
22
+ "latents_std": null,
23
+ "layers_per_block": 2,
24
+ "norm_num_groups": 32,
25
+ "out_channels": 3,
26
+ "sample_size": 512,
27
+ "scaling_factor": 0.18215,
28
+ "up_block_types": [
29
+ "UpDecoderBlock2D",
30
+ "UpDecoderBlock2D",
31
+ "UpDecoderBlock2D",
32
+ "UpDecoderBlock2D"
33
+ ]
34
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c
3
+ size 167335342