Deepshikha11 commited on
Commit
65ff4ff
·
verified ·
1 Parent(s): fc4e964

End of training

Browse files
Files changed (36) hide show
  1. README.md +39 -0
  2. checkpoint-1000/model.safetensors +3 -0
  3. checkpoint-1000/optimizer.bin +3 -0
  4. checkpoint-1000/random_states_0.pkl +3 -0
  5. checkpoint-1000/scaler.pt +3 -0
  6. checkpoint-1000/scheduler.bin +3 -0
  7. checkpoint-500/model.safetensors +3 -0
  8. checkpoint-500/optimizer.bin +3 -0
  9. checkpoint-500/random_states_0.pkl +3 -0
  10. checkpoint-500/scaler.pt +3 -0
  11. checkpoint-500/scheduler.bin +3 -0
  12. feature_extractor/preprocessor_config.json +27 -0
  13. learned_embeds-steps-1000.safetensors +3 -0
  14. learned_embeds-steps-500.safetensors +3 -0
  15. learned_embeds.safetensors +3 -0
  16. logs/textual_inversion/1743485291.8752425/events.out.tfevents.1743485291.deepshikha.304592.1 +3 -0
  17. logs/textual_inversion/1743485291.8761997/hparams.yml +48 -0
  18. logs/textual_inversion/1743485338.8943248/events.out.tfevents.1743485338.deepshikha.305396.1 +3 -0
  19. logs/textual_inversion/1743485338.895232/hparams.yml +48 -0
  20. logs/textual_inversion/events.out.tfevents.1743485291.deepshikha.304592.0 +3 -0
  21. logs/textual_inversion/events.out.tfevents.1743485338.deepshikha.305396.0 +3 -0
  22. model_index.json +38 -0
  23. safety_checker/config.json +47 -0
  24. safety_checker/model.safetensors +3 -0
  25. scheduler/scheduler_config.json +15 -0
  26. text_encoder/config.json +24 -0
  27. text_encoder/model.safetensors +3 -0
  28. tokenizer/added_tokens.json +3 -0
  29. tokenizer/merges.txt +0 -0
  30. tokenizer/special_tokens_map.json +24 -0
  31. tokenizer/tokenizer_config.json +39 -0
  32. tokenizer/vocab.json +0 -0
  33. unet/config.json +68 -0
  34. unet/diffusion_pytorch_model.safetensors +3 -0
  35. vae/config.json +38 -0
  36. vae/diffusion_pytorch_model.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: runwayml/stable-diffusion-v1-5
3
+ library_name: diffusers
4
+ license: creativeml-openrail-m
5
+ inference: true
6
+ tags:
7
+ - stable-diffusion
8
+ - stable-diffusion-diffusers
9
+ - text-to-image
10
+ - diffusers
11
+ - textual_inversion
12
+ - diffusers-training
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the training script had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+
19
+ # Textual inversion text2image fine-tuning - Deepshikha11/textual_inversion_cat
20
+ These are textual inversion adaption weights for runwayml/stable-diffusion-v1-5. You can find some example images in the following.
21
+
22
+
23
+
24
+
25
+ ## Intended uses & limitations
26
+
27
+ #### How to use
28
+
29
+ ```python
30
+ # TODO: add an example code snippet for running this diffusion pipeline
31
+ ```
32
+
33
+ #### Limitations and bias
34
+
35
+ [TODO: provide examples of latent issues and potential remediations]
36
+
37
+ ## Training details
38
+
39
+ [TODO: describe the data used to train the model]
checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c53b95bd5b0abba64a8f81ff66a66de3aa99849185296aec1c5e903757aad01
3
+ size 492268240
checkpoint-1000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:665f4905dd3c95d9a53752ce761a49e4a28c6dc35ef0afb7fd110f646a5cfd64
3
+ size 303570914
checkpoint-1000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e282ee59149259ed3ed7cf59004dc4cd76a35a84f22dbd60568c2e192a509a75
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 sha256:3f0d829441992ff2ab1f7502a3a94afc011706461052e42e18e5b963678527c4
3
+ size 1000
checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b292cead47d6f658d3261fd67882d42fc893f0a46636d2ee2aa5bb6fccd544c0
3
+ size 492268240
checkpoint-500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:328af9306a6f8683ee04d504d672fdd7f4c1ba9954eeb7290f8a2d83ca28b616
3
+ size 303570914
checkpoint-500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94018625aca75266327fb3f6af376d7f97d2fb541b518abcd74b736ac0f1a2c1
3
+ size 14344
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 sha256:8cad514bb36617120f19b7cde3b36a22bc8becf6cc6cfb2166811645c215cccb
3
+ size 1000
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 224
26
+ }
27
+ }
learned_embeds-steps-1000.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f8b366499933d5633d73f3e130ccd318ddd21c121d4a5b7619ee0078035ddcc
3
+ size 3184
learned_embeds-steps-500.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0350966d23269ae9c36d69c8c323573a1c02441354cdfb8050dc135ba86dd5b3
3
+ size 3184
learned_embeds.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f8b366499933d5633d73f3e130ccd318ddd21c121d4a5b7619ee0078035ddcc
3
+ size 3184
logs/textual_inversion/1743485291.8752425/events.out.tfevents.1743485291.deepshikha.304592.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b79866a06b782ae7f9f64d1bd39317fa8ab622278890946c9bad5541ec7304c
3
+ size 2332
logs/textual_inversion/1743485291.8761997/hparams.yml ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ center_crop: false
7
+ checkpointing_steps: 500
8
+ checkpoints_total_limit: null
9
+ dataloader_num_workers: 0
10
+ enable_xformers_memory_efficient_attention: false
11
+ gradient_accumulation_steps: 4
12
+ gradient_checkpointing: false
13
+ hub_model_id: null
14
+ hub_token: null
15
+ initializer_token: toy
16
+ learnable_property: object
17
+ learning_rate: 0.002
18
+ local_rank: -1
19
+ logging_dir: logs
20
+ lr_num_cycles: 1
21
+ lr_scheduler: constant
22
+ lr_warmup_steps: 0
23
+ max_train_steps: 1000
24
+ mixed_precision: fp16
25
+ no_safe_serialization: false
26
+ num_train_epochs: 6
27
+ num_validation_images: 4
28
+ num_vectors: 1
29
+ output_dir: textual_inversion_cat
30
+ placeholder_token: <cat-toy>
31
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
32
+ push_to_hub: true
33
+ repeats: 100
34
+ report_to: tensorboard
35
+ resolution: 256
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ save_as_full_pipeline: false
39
+ save_steps: 500
40
+ scale_lr: true
41
+ seed: null
42
+ tokenizer_name: null
43
+ train_batch_size: 1
44
+ train_data_dir: ../../../cat
45
+ validation_epochs: null
46
+ validation_prompt: null
47
+ validation_steps: 100
48
+ variant: null
logs/textual_inversion/1743485338.8943248/events.out.tfevents.1743485338.deepshikha.305396.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43186948ddb5bc30270e69462b474bf77b6d91c5fc5c6cbd47bcd6446065c1b3
3
+ size 2332
logs/textual_inversion/1743485338.895232/hparams.yml ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ center_crop: false
7
+ checkpointing_steps: 500
8
+ checkpoints_total_limit: null
9
+ dataloader_num_workers: 0
10
+ enable_xformers_memory_efficient_attention: false
11
+ gradient_accumulation_steps: 4
12
+ gradient_checkpointing: false
13
+ hub_model_id: null
14
+ hub_token: null
15
+ initializer_token: toy
16
+ learnable_property: object
17
+ learning_rate: 0.002
18
+ local_rank: -1
19
+ logging_dir: logs
20
+ lr_num_cycles: 1
21
+ lr_scheduler: constant
22
+ lr_warmup_steps: 0
23
+ max_train_steps: 1000
24
+ mixed_precision: fp16
25
+ no_safe_serialization: false
26
+ num_train_epochs: 7
27
+ num_validation_images: 4
28
+ num_vectors: 1
29
+ output_dir: textual_inversion_cat
30
+ placeholder_token: <cat-toy>
31
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
32
+ push_to_hub: true
33
+ repeats: 100
34
+ report_to: tensorboard
35
+ resolution: 256
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ save_as_full_pipeline: false
39
+ save_steps: 500
40
+ scale_lr: true
41
+ seed: null
42
+ tokenizer_name: null
43
+ train_batch_size: 1
44
+ train_data_dir: ../../../cat
45
+ validation_epochs: null
46
+ validation_prompt: null
47
+ validation_steps: 100
48
+ variant: null
logs/textual_inversion/events.out.tfevents.1743485291.deepshikha.304592.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a93d1acfbed26fe2596fd4286a6cab02b89ce866eb97b7247b0081803933da70
3
+ size 486
logs/textual_inversion/events.out.tfevents.1743485338.deepshikha.305396.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07dc48e9ad40a3b03edb612b78ebc96f48ff06e2b96f56ae15eaec4000b7d71e
3
+ size 335054
model_index.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.33.0.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 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "StableDiffusionSafetyChecker"
4
+ ],
5
+ "initializer_factor": 1.0,
6
+ "logit_scale_init_value": 2.6592,
7
+ "model_type": "clip",
8
+ "projection_dim": 768,
9
+ "text_config": {
10
+ "attention_dropout": 0.0,
11
+ "dropout": 0.0,
12
+ "hidden_act": "quick_gelu",
13
+ "hidden_size": 768,
14
+ "initializer_factor": 1.0,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "layer_norm_eps": 1e-05,
18
+ "max_position_embeddings": 77,
19
+ "model_type": "clip_text_model",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "projection_dim": 512,
23
+ "torch_dtype": "float32",
24
+ "vocab_size": 49408
25
+ },
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.50.2",
28
+ "vision_config": {
29
+ "_attn_implementation_autoset": true,
30
+ "attention_dropout": 0.0,
31
+ "dropout": 0.0,
32
+ "hidden_act": "quick_gelu",
33
+ "hidden_size": 1024,
34
+ "image_size": 224,
35
+ "initializer_factor": 1.0,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 4096,
38
+ "layer_norm_eps": 1e-05,
39
+ "model_type": "clip_vision_model",
40
+ "num_attention_heads": 16,
41
+ "num_channels": 3,
42
+ "num_hidden_layers": 24,
43
+ "patch_size": 14,
44
+ "projection_dim": 512,
45
+ "torch_dtype": "float32"
46
+ }
47
+ }
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": "0.33.0.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 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CLIPTextModel"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 0,
7
+ "dropout": 0.0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "quick_gelu",
10
+ "hidden_size": 768,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 77,
16
+ "model_type": "clip_text_model",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "projection_dim": 768,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.50.2",
23
+ "vocab_size": 49409
24
+ }
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c53b95bd5b0abba64a8f81ff66a66de3aa99849185296aec1c5e903757aad01
3
+ size 492268240
tokenizer/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<cat-toy>": 49408
3
+ }
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 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "49408": {
21
+ "content": "<cat-toy>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ }
28
+ },
29
+ "bos_token": "<|startoftext|>",
30
+ "clean_up_tokenization_spaces": false,
31
+ "do_lower_case": true,
32
+ "eos_token": "<|endoftext|>",
33
+ "errors": "replace",
34
+ "extra_special_tokens": {},
35
+ "model_max_length": 77,
36
+ "pad_token": "<|endoftext|>",
37
+ "tokenizer_class": "CLIPTokenizer",
38
+ "unk_token": "<|endoftext|>"
39
+ }
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": "0.33.0.dev0",
4
+ "_name_or_path": "runwayml/stable-diffusion-v1-5",
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": 4,
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:c83908253f9a64d08c25fc90874c9c8aef9a329ce1ca5fb909d73b0c83d1ea21
3
+ size 1719125304
vae/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.33.0.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
+ "mid_block_add_attention": true,
25
+ "norm_num_groups": 32,
26
+ "out_channels": 3,
27
+ "sample_size": 512,
28
+ "scaling_factor": 0.18215,
29
+ "shift_factor": null,
30
+ "up_block_types": [
31
+ "UpDecoderBlock2D",
32
+ "UpDecoderBlock2D",
33
+ "UpDecoderBlock2D",
34
+ "UpDecoderBlock2D"
35
+ ],
36
+ "use_post_quant_conv": true,
37
+ "use_quant_conv": true
38
+ }
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