heale22 commited on
Commit
d9f4f2f
1 Parent(s): 1a915f2

End of training

Browse files
Files changed (45) hide show
  1. README.md +43 -0
  2. checkpoint-5000/model.safetensors +3 -0
  3. checkpoint-5000/optimizer.bin +3 -0
  4. checkpoint-5000/random_states_0.pkl +3 -0
  5. checkpoint-5000/scheduler.bin +3 -0
  6. feature_extractor/preprocessor_config.json +44 -0
  7. image_0.png +0 -0
  8. image_1.png +0 -0
  9. image_2.png +0 -0
  10. image_3.png +0 -0
  11. learned_embeds-steps-1000.bin +3 -0
  12. learned_embeds-steps-1500.bin +3 -0
  13. learned_embeds-steps-2000.bin +3 -0
  14. learned_embeds-steps-2500.bin +3 -0
  15. learned_embeds-steps-3000.bin +3 -0
  16. learned_embeds-steps-3500.bin +3 -0
  17. learned_embeds-steps-4000.bin +3 -0
  18. learned_embeds-steps-4500.bin +3 -0
  19. learned_embeds-steps-500.bin +3 -0
  20. learned_embeds-steps-5000.bin +3 -0
  21. learned_embeds.bin +3 -0
  22. logs/textual_inversion/1718248018.6333783/events.out.tfevents.1718248018.deep-chungus-4.csail.mit.edu.3397439.1 +3 -0
  23. logs/textual_inversion/1718248018.6498396/hparams.yml +49 -0
  24. logs/textual_inversion/1718303074.872746/events.out.tfevents.1718303074.deep-chungus-4.csail.mit.edu.722649.1 +3 -0
  25. logs/textual_inversion/1718303074.8948605/hparams.yml +49 -0
  26. logs/textual_inversion/1718328881.1141868/events.out.tfevents.1718328881.deep-chungus-5.csail.mit.edu.1991989.1 +3 -0
  27. logs/textual_inversion/1718328881.132989/hparams.yml +49 -0
  28. logs/textual_inversion/events.out.tfevents.1718248018.deep-chungus-4.csail.mit.edu.3397439.0 +3 -0
  29. logs/textual_inversion/events.out.tfevents.1718303074.deep-chungus-4.csail.mit.edu.722649.0 +3 -0
  30. logs/textual_inversion/events.out.tfevents.1718328881.deep-chungus-5.csail.mit.edu.1991989.0 +3 -0
  31. model_index.json +38 -0
  32. safety_checker/config.json +28 -0
  33. safety_checker/model.safetensors +3 -0
  34. scheduler/scheduler_config.json +15 -0
  35. text_encoder/config.json +25 -0
  36. text_encoder/model.safetensors +3 -0
  37. tokenizer/added_tokens.json +3 -0
  38. tokenizer/merges.txt +0 -0
  39. tokenizer/special_tokens_map.json +24 -0
  40. tokenizer/tokenizer_config.json +38 -0
  41. tokenizer/vocab.json +0 -0
  42. unet/config.json +68 -0
  43. unet/diffusion_pytorch_model.safetensors +3 -0
  44. vae/config.json +34 -0
  45. vae/diffusion_pytorch_model.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: creativeml-openrail-m
3
+ library_name: diffusers
4
+ tags:
5
+ - stable-diffusion
6
+ - stable-diffusion-diffusers
7
+ - text-to-image
8
+ - diffusers
9
+ - textual_inversion
10
+ - diffusers-training
11
+ base_model: CompVis/stable-diffusion-v1-4
12
+ inference: true
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 - heale22/chairs_inversion_2-5e-3_5000steps_largetoken
20
+ These are textual inversion adaption weights for CompVis/stable-diffusion-v1-4. You can find some example images in the following.
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
+
29
+ ## Intended uses & limitations
30
+
31
+ #### How to use
32
+
33
+ ```python
34
+ # TODO: add an example code snippet for running this diffusion pipeline
35
+ ```
36
+
37
+ #### Limitations and bias
38
+
39
+ [TODO: provide examples of latent issues and potential remediations]
40
+
41
+ ## Training details
42
+
43
+ [TODO: describe the data used to train the model]
checkpoint-5000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8652aa7ae77d4c2d56700cafb372ce740790d74db25d61ae58699defe890ba6e
3
+ size 492268240
checkpoint-5000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9a7cc47241cb23f3fb48078359dfa2720f5b53a100eca9deb5df1186f31153a
3
+ size 303570914
checkpoint-5000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32678ae0a003f337f858ea70488da7b973d56a7c8fa4521490fb0cc7a5c71ac2
3
+ size 14344
checkpoint-5000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a00575b42e786b20605b603e100fe98250d51f62e3ea20150fbf3333bfbb698
3
+ size 1000
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
+ }
image_0.png ADDED
image_1.png ADDED
image_2.png ADDED
image_3.png ADDED
learned_embeds-steps-1000.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfa3ea9c0b9ce474fc483e037ddbb216ee7fe494aa7185c615afb2efe2daf5cd
3
+ size 4470
learned_embeds-steps-1500.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beb04f80b54515c49753f58a5f0d94bb68d7ae62c04dd91406cc74bdde407d92
3
+ size 4470
learned_embeds-steps-2000.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c54fe356640b832bcd1fe6dc9b678c5717d0a9bbd750ae8ca64d597cb146951
3
+ size 4470
learned_embeds-steps-2500.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66c51dd03bcd9f80d3e3237e2204c1cc2f5ce5aecceb466def17e6bd0241a8ba
3
+ size 4470
learned_embeds-steps-3000.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:277afbc5e2e70723a322abbf0874a87eb48780ea0c41c738620b2073da42e354
3
+ size 4470
learned_embeds-steps-3500.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94931df01719b4d5d8aa2ead296e6278c8c079af326a54d0200c21bcb976b09d
3
+ size 4470
learned_embeds-steps-4000.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a733c033fbf80d42458bb581fa800549d886b66128b6a7954a9a34cadded01ce
3
+ size 4470
learned_embeds-steps-4500.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e8b2265258c767408b12779b727025da31e450df5d878ea02116bd09d3adafc
3
+ size 4470
learned_embeds-steps-500.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db6bad2315da9e008592e5412def7f6725a299a1ae2a2b0f187a6d4708fb7d67
3
+ size 4465
learned_embeds-steps-5000.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e95de622434d8473da4708a1d2fe2147dacde6f1f0e36f8303b6f48c25035198
3
+ size 4470
learned_embeds.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e147d22334cb99ed41a1df95193664a48ac83bbf450d3eb056a8774e4b627a43
3
+ size 4287
logs/textual_inversion/1718248018.6333783/events.out.tfevents.1718248018.deep-chungus-4.csail.mit.edu.3397439.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ab627ebca7071bd0d8fcf7366bdaaed2aa5cb4bc7597523d19165d2d1a45181
3
+ size 2488
logs/textual_inversion/1718248018.6498396/hparams.yml ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 5000
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: chair
16
+ learnable_property: object
17
+ learning_rate: 0.04
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: 5000
24
+ mixed_precision: 'no'
25
+ model_name_unique: null
26
+ no_safe_serialization: true
27
+ num_train_epochs: 88
28
+ num_validation_images: 4
29
+ num_vectors: 1
30
+ output_dir: /mnt/xfs/home/alexh22/erasing/chairs_inversion_2-5e-3_5000steps_largetoken
31
+ placeholder_token: <al-ex-ch-air>
32
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
33
+ push_to_hub: true
34
+ repeats: 100
35
+ report_to: tensorboard
36
+ resolution: 512
37
+ resume_from_checkpoint: null
38
+ revision: null
39
+ save_as_full_pipeline: true
40
+ save_steps: 500
41
+ scale_lr: true
42
+ seed: null
43
+ tokenizer_name: null
44
+ train_batch_size: 4
45
+ train_data_dir: /mnt/xfs/home/alexh22/erasing/chairs
46
+ validation_epochs: null
47
+ validation_prompt: A photo of a <al-ex-ch-air>
48
+ validation_steps: 100
49
+ variant: null
logs/textual_inversion/1718303074.872746/events.out.tfevents.1718303074.deep-chungus-4.csail.mit.edu.722649.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cb842da64d10d68bb3c54d8fed01eca4870a9f704924dc5dd7accc741a56abd
3
+ size 2488
logs/textual_inversion/1718303074.8948605/hparams.yml ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 5000
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: chair
16
+ learnable_property: object
17
+ learning_rate: 0.04
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: 5000
24
+ mixed_precision: 'no'
25
+ model_name_unique: null
26
+ no_safe_serialization: true
27
+ num_train_epochs: 88
28
+ num_validation_images: 4
29
+ num_vectors: 1
30
+ output_dir: /mnt/xfs/home/alexh22/erasing/chairs_inversion_2-5e-3_5000steps_largetoken
31
+ placeholder_token: <al-ex-ch-air>
32
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
33
+ push_to_hub: true
34
+ repeats: 100
35
+ report_to: tensorboard
36
+ resolution: 512
37
+ resume_from_checkpoint: null
38
+ revision: null
39
+ save_as_full_pipeline: true
40
+ save_steps: 500
41
+ scale_lr: true
42
+ seed: null
43
+ tokenizer_name: null
44
+ train_batch_size: 4
45
+ train_data_dir: /mnt/xfs/home/alexh22/erasing/chairs
46
+ validation_epochs: null
47
+ validation_prompt: A photo of a <al-ex-ch-air>
48
+ validation_steps: 100
49
+ variant: null
logs/textual_inversion/1718328881.1141868/events.out.tfevents.1718328881.deep-chungus-5.csail.mit.edu.1991989.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b0943fdc8409330439207438a938ae0a5c00ed67963be6efa4d8cc928cdcee7
3
+ size 2488
logs/textual_inversion/1718328881.132989/hparams.yml ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 5000
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: chair
16
+ learnable_property: object
17
+ learning_rate: 0.04
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: 5000
24
+ mixed_precision: 'no'
25
+ model_name_unique: null
26
+ no_safe_serialization: true
27
+ num_train_epochs: 88
28
+ num_validation_images: 4
29
+ num_vectors: 1
30
+ output_dir: /mnt/xfs/home/alexh22/erasing/chairs_inversion_2-5e-3_5000steps_largetoken
31
+ placeholder_token: <al-ex-ch-air>
32
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
33
+ push_to_hub: true
34
+ repeats: 100
35
+ report_to: tensorboard
36
+ resolution: 512
37
+ resume_from_checkpoint: null
38
+ revision: null
39
+ save_as_full_pipeline: true
40
+ save_steps: 500
41
+ scale_lr: true
42
+ seed: null
43
+ tokenizer_name: null
44
+ train_batch_size: 4
45
+ train_data_dir: /mnt/xfs/home/alexh22/erasing/chairs
46
+ validation_epochs: null
47
+ validation_prompt: A photo of a <al-ex-ch-air>
48
+ validation_steps: 100
49
+ variant: null
logs/textual_inversion/events.out.tfevents.1718248018.deep-chungus-4.csail.mit.edu.3397439.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eefadbb388e12bd4ddc6bc90a6e6a88220197d5b2ad38eefd0f5438db8c8f705
3
+ size 88
logs/textual_inversion/events.out.tfevents.1718303074.deep-chungus-4.csail.mit.edu.722649.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd0b40c10c4a59865ffd18f8086f1cab45b2588df2f6c9a225d8ad91f3dcdaa2
3
+ size 52907910
logs/textual_inversion/events.out.tfevents.1718328881.deep-chungus-5.csail.mit.edu.1991989.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4df52c924973a0ab163bdeadcb4d63b858ed7c2fd5387bd3adfb4fc0739e658
3
+ size 89914255
model_index.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.29.0.dev0",
4
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
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": "/mnt/xfs/home/alexh22/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/133a221b8aa7292a167afc5127cb63fb5005638b/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": "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": "float32",
23
+ "transformers_version": "4.41.2",
24
+ "vocab_size": 49409
25
+ }
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8652aa7ae77d4c2d56700cafb372ce740790d74db25d61ae58699defe890ba6e
3
+ size 492268240
tokenizer/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<al-ex-ch-air>": 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 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<al-ex-ch-air>",
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": true,
31
+ "do_lower_case": true,
32
+ "eos_token": "<|endoftext|>",
33
+ "errors": "replace",
34
+ "model_max_length": 77,
35
+ "pad_token": "<|endoftext|>",
36
+ "tokenizer_class": "CLIPTokenizer",
37
+ "unk_token": "<|endoftext|>"
38
+ }
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": "CompVis/stable-diffusion-v1-4",
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:d54d1800033f872c2ede03a45de06d176a53146e43bc9bdb81b0429560a07dc9
3
+ size 3438167536
vae/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.29.0.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
+ "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:b4d2b5932bb4151e54e694fd31ccf51fca908223c9485bd56cd0e1d83ad94c49
3
+ size 334643268