ashnrk commited on
Commit
763ed4d
1 Parent(s): d9e8317

End of training

Browse files
Files changed (49) hide show
  1. README.md +17 -0
  2. checkpoint-1000/optimizer.bin +3 -0
  3. checkpoint-1000/pytorch_model.bin +3 -0
  4. checkpoint-1000/random_states_0.pkl +3 -0
  5. checkpoint-1000/scheduler.bin +3 -0
  6. checkpoint-1500/optimizer.bin +3 -0
  7. checkpoint-1500/pytorch_model.bin +3 -0
  8. checkpoint-1500/random_states_0.pkl +3 -0
  9. checkpoint-1500/scheduler.bin +3 -0
  10. checkpoint-2000/optimizer.bin +3 -0
  11. checkpoint-2000/pytorch_model.bin +3 -0
  12. checkpoint-2000/random_states_0.pkl +3 -0
  13. checkpoint-2000/scheduler.bin +3 -0
  14. checkpoint-2500/optimizer.bin +3 -0
  15. checkpoint-2500/pytorch_model.bin +3 -0
  16. checkpoint-2500/random_states_0.pkl +3 -0
  17. checkpoint-2500/scheduler.bin +3 -0
  18. checkpoint-3000/optimizer.bin +3 -0
  19. checkpoint-3000/pytorch_model.bin +3 -0
  20. checkpoint-3000/random_states_0.pkl +3 -0
  21. checkpoint-3000/scheduler.bin +3 -0
  22. checkpoint-500/optimizer.bin +3 -0
  23. checkpoint-500/pytorch_model.bin +3 -0
  24. checkpoint-500/random_states_0.pkl +3 -0
  25. checkpoint-500/scheduler.bin +3 -0
  26. feature_extractor/preprocessor_config.json +28 -0
  27. learned_embeds-steps-1000.bin +3 -0
  28. learned_embeds-steps-1500.bin +3 -0
  29. learned_embeds-steps-2000.bin +3 -0
  30. learned_embeds-steps-2500.bin +3 -0
  31. learned_embeds-steps-3000.bin +3 -0
  32. learned_embeds-steps-500.bin +3 -0
  33. learned_embeds.bin +3 -0
  34. logs/textual_inversion/1689072905.693046/events.out.tfevents.1689072905.ip-172-31-25-234.1798668.1 +3 -0
  35. logs/textual_inversion/1689072905.6944845/hparams.yml +46 -0
  36. logs/textual_inversion/events.out.tfevents.1689072905.ip-172-31-25-234.1798668.0 +3 -0
  37. model_index.json +33 -0
  38. scheduler/scheduler_config.json +20 -0
  39. text_encoder/config.json +25 -0
  40. text_encoder/pytorch_model.bin +3 -0
  41. tokenizer/added_tokens.json +3 -0
  42. tokenizer/merges.txt +0 -0
  43. tokenizer/special_tokens_map.json +24 -0
  44. tokenizer/tokenizer_config.json +33 -0
  45. tokenizer/vocab.json +0 -0
  46. unet/config.json +67 -0
  47. unet/diffusion_pytorch_model.bin +3 -0
  48. vae/config.json +31 -0
  49. vae/diffusion_pytorch_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: creativeml-openrail-m
4
+ base_model: stabilityai/stable-diffusion-2-1
5
+ tags:
6
+ - stable-diffusion
7
+ - stable-diffusion-diffusers
8
+ - text-to-image
9
+ - diffusers
10
+ - textual_inversion
11
+ inference: true
12
+ ---
13
+
14
+ # Textual inversion text2image fine-tuning - ashnrk/textual_inversion_perm_crop
15
+ These are textual inversion adaption weights for stabilityai/stable-diffusion-2-1. You can find some example images in the following.
16
+
17
+
checkpoint-1000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c0d1450c67851c98eb06f0c1e81521d0e7617dbae8519ba3e40cb2484ec54da
3
+ size 404760109
checkpoint-1000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab51ec247aa328ded5342793ebb2ab834f3fdb26a9edf0e6f7a2ce0ab2878a70
3
+ size 1361701921
checkpoint-1000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b3896b58dc0ed3a7722bacc9db183409265fb7b83a781b00bcd5c18c9864b14
3
+ size 21731
checkpoint-1000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4fefee7f0cd3cd72549c0d880d30f20865cdb0b9e2ff7f6414504c4b2e9f0da
3
+ size 563
checkpoint-1500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56d5e355c8aacc2a5c82d9f8a995fb704475f0d579c07ff55b445f9b80355b08
3
+ size 404760109
checkpoint-1500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09d3db51e38d73ae793a68e82a2cef46fa4a00493644ec953bc527047d7dbe82
3
+ size 1361701921
checkpoint-1500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a90c5aab54e020b11dcef62db9e05d79d5e8d3c64ea7a8654a4eb8347c93c7b8
3
+ size 21795
checkpoint-1500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:844da8963017941e63785b9c97b8add92acc2cd25941c28fb340a858881df1bf
3
+ size 563
checkpoint-2000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0a8ac78073611ecef0b6a95e76d238f52ffc6a507e77b8cf92ea337a8ccbc93
3
+ size 404760109
checkpoint-2000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df45ba374e467f49414ceb4858ad9404bdd53e9dd5038073c10a0ec37acf21a4
3
+ size 1361701921
checkpoint-2000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:994f02470986883505352297f54d6ce7a14dd4e945689fbe56612ef4fe9ae7d5
3
+ size 21731
checkpoint-2000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbf4fc1f2d7f293314583514528a85b4410bc5064cfda7e58674f7e1d643273c
3
+ size 563
checkpoint-2500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d7f03af363e034d44334faaf2a2bf348922418365ad01c018c72f638d8273fb
3
+ size 404760109
checkpoint-2500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c8b64287bf2168860a95de05b255670c07ab174b7500750e6f324176a7f759b
3
+ size 1361701921
checkpoint-2500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f7086d80246559be65a60008630fd835633dafb11c2608386dca765851caf70
3
+ size 21795
checkpoint-2500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4740df90e3b20bbc1c987eb976fb0a841bb921549ef0b5da564eb30b6591fa90
3
+ size 563
checkpoint-3000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ced3c404ac6eef9de332afa88f71143ed2b7696bb130950794f91381b0bd437
3
+ size 404760109
checkpoint-3000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c72d244c3c5c06d8d91c3b739ea2f1a79b82927656693abbc8279d5cd5a0de1f
3
+ size 1361701921
checkpoint-3000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50fbb95969f35f7e1592c930c42e61d42ced51ba36c7336849dc748422a4d16d
3
+ size 21795
checkpoint-3000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40a514eb416e461c32b87bc59fb69f01b75bd71e657d33697170ae8eab25546d
3
+ size 563
checkpoint-500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:547600509168de8236305fa49603bd966a5fa2852d4378b9d4b66b8ea086596f
3
+ size 404760109
checkpoint-500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:806c7b61cdd37c594740b335709d3d14db24eeeccc0635fe4cc0110eb954125a
3
+ size 1361701921
checkpoint-500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c583219302242893ed8033e5ffc8e60a9edecbbeee150cb6d999d0d96d2a8cc
3
+ size 21795
checkpoint-500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4033b05306d90c4d61604702df45c09b47067814076296e9dc54ee6e1e25ece5
3
+ size 563
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": "CLIPImageProcessor",
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
+ }
learned_embeds-steps-1000.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:382637a7d15512e29075632e63030528aa825cb4de7df1df92f0db3c37b9c22d
3
+ size 5025
learned_embeds-steps-1500.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2d34f8d0130240f88f2c28e9b3b2836961db21b80ad86d0e52ac01cd4aa3039
3
+ size 5025
learned_embeds-steps-2000.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:855f428b46c2b63a82b8755b42005953522b7559340938641638dcd2a2e64e43
3
+ size 5025
learned_embeds-steps-2500.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cad3dee7a1be21e474c4aa757b226944439113fcc09e305cebc5c04f1a9a970
3
+ size 5025
learned_embeds-steps-3000.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf5f90d04443ebfa0ef6c02cc9309f3b077e6de7900369ca1785378f3fead0c1
3
+ size 5025
learned_embeds-steps-500.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f57f5716f03afc9126d2a96bd31425e4409bba3a2907ca4b65e18da468d2ae5e
3
+ size 5022
learned_embeds.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63334efc8fe67431aa108500c7a716554c7d754b893f295c74b59e419909a390
3
+ size 4864
logs/textual_inversion/1689072905.693046/events.out.tfevents.1689072905.ip-172-31-25-234.1798668.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f202fce608a51b5b47b5a19590d250711c176625c61554f14c332cbf6656b7a
3
+ size 2325
logs/textual_inversion/1689072905.6944845/hparams.yml ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: true
11
+ gradient_accumulation_steps: 4
12
+ gradient_checkpointing: false
13
+ hub_model_id: null
14
+ hub_token: null
15
+ initializer_token: farm
16
+ learnable_property: object
17
+ learning_rate: 0.016
18
+ local_rank: 0
19
+ logging_dir: logs
20
+ lr_num_cycles: 1
21
+ lr_scheduler: constant
22
+ lr_warmup_steps: 0
23
+ max_train_steps: 3000
24
+ mixed_precision: 'no'
25
+ num_train_epochs: 94
26
+ num_validation_images: 4
27
+ num_vectors: 1
28
+ output_dir: textual_inversion_perm_crop
29
+ placeholder_token: <perm-crop-sat>
30
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
31
+ push_to_hub: true
32
+ repeats: 100
33
+ report_to: tensorboard
34
+ resolution: 512
35
+ resume_from_checkpoint: null
36
+ revision: null
37
+ save_as_full_pipeline: false
38
+ save_steps: 500
39
+ scale_lr: true
40
+ seed: null
41
+ tokenizer_name: null
42
+ train_batch_size: 1
43
+ train_data_dir: /home/ubuntu/datasets/Eurosat_few_shot_10/PermanentCrop
44
+ validation_epochs: null
45
+ validation_prompt: null
46
+ validation_steps: 100
logs/textual_inversion/events.out.tfevents.1689072905.ip-172-31-25-234.1798668.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92b58dfa81cb85c3f7231dc605e21de08ef8cea4ce93d8c8d59c5b7829857ab2
3
+ size 983642
model_index.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.18.0.dev0",
4
+ "feature_extractor": [
5
+ "transformers",
6
+ "CLIPImageProcessor"
7
+ ],
8
+ "requires_safety_checker": false,
9
+ "safety_checker": [
10
+ null,
11
+ null
12
+ ],
13
+ "scheduler": [
14
+ "diffusers",
15
+ "DDIMScheduler"
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
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDIMScheduler",
3
+ "_diffusers_version": "0.18.0.dev0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "clip_sample_range": 1.0,
9
+ "dynamic_thresholding_ratio": 0.995,
10
+ "num_train_timesteps": 1000,
11
+ "prediction_type": "v_prediction",
12
+ "rescale_betas_zero_snr": false,
13
+ "sample_max_value": 1.0,
14
+ "set_alpha_to_one": false,
15
+ "skip_prk_steps": true,
16
+ "steps_offset": 1,
17
+ "thresholding": false,
18
+ "timestep_spacing": "leading",
19
+ "trained_betas": null
20
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
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": "gelu",
11
+ "hidden_size": 1024,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 23,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 512,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.30.1",
24
+ "vocab_size": 49409
25
+ }
text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eecfdd7a311f5684db0c1fa3ca8316aedf6544aa805cb5b3975e7061eafcd766
3
+ size 1361684001
tokenizer/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<perm-crop-sat>": 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": "!",
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 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": true,
12
+ "do_lower_case": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 77,
23
+ "pad_token": "<|endoftext|>",
24
+ "tokenizer_class": "CLIPTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.18.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "attention_head_dim": [
9
+ 5,
10
+ 10,
11
+ 20,
12
+ 20
13
+ ],
14
+ "block_out_channels": [
15
+ 320,
16
+ 640,
17
+ 1280,
18
+ 1280
19
+ ],
20
+ "center_input_sample": false,
21
+ "class_embed_type": null,
22
+ "class_embeddings_concat": false,
23
+ "conv_in_kernel": 3,
24
+ "conv_out_kernel": 3,
25
+ "cross_attention_dim": 1024,
26
+ "cross_attention_norm": null,
27
+ "down_block_types": [
28
+ "CrossAttnDownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D",
31
+ "DownBlock2D"
32
+ ],
33
+ "downsample_padding": 1,
34
+ "dual_cross_attention": false,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "in_channels": 4,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "norm_eps": 1e-05,
45
+ "norm_num_groups": 32,
46
+ "num_class_embeds": null,
47
+ "only_cross_attention": false,
48
+ "out_channels": 4,
49
+ "projection_class_embeddings_input_dim": null,
50
+ "resnet_out_scale_factor": 1.0,
51
+ "resnet_skip_time_act": false,
52
+ "resnet_time_scale_shift": "default",
53
+ "sample_size": 96,
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
+ "up_block_types": [
60
+ "UpBlock2D",
61
+ "CrossAttnUpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D"
64
+ ],
65
+ "upcast_attention": true,
66
+ "use_linear_projection": true
67
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29c7f15709062e790deddc2c6d3d6a3e0a99d4a533b6bfd187bdea64a5e7a961
3
+ size 3463934693
vae/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.18.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
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": 768,
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 sha256:185b0c03485b4048bb6158de087df301b79ea187844c76ae91cd4cda207282a2
3
+ size 334715569