shrikant11 commited on
Commit
a7d102b
1 Parent(s): d72700a

End of training

Browse files
Files changed (30) hide show
  1. .gitattributes +1 -0
  2. README.md +48 -0
  3. feature_extractor/preprocessor_config.json +29 -0
  4. logs/text2image-fine-tune/1704350095.1492045/events.out.tfevents.1704350095.4ce07924bfdd.758.1 +3 -0
  5. logs/text2image-fine-tune/1704350095.150961/hparams.yml +52 -0
  6. logs/text2image-fine-tune/1704352186.779532/events.out.tfevents.1704352186.4ce07924bfdd.758.3 +3 -0
  7. logs/text2image-fine-tune/1704352186.7812426/hparams.yml +52 -0
  8. logs/text2image-fine-tune/1704352337.3800864/events.out.tfevents.1704352337.4ce07924bfdd.758.5 +3 -0
  9. logs/text2image-fine-tune/1704352337.3818705/hparams.yml +52 -0
  10. logs/text2image-fine-tune/1704352528.06429/events.out.tfevents.1704352528.4ce07924bfdd.758.7 +3 -0
  11. logs/text2image-fine-tune/1704352528.0660906/hparams.yml +52 -0
  12. logs/text2image-fine-tune/events.out.tfevents.1704350095.4ce07924bfdd.758.0 +3 -0
  13. logs/text2image-fine-tune/events.out.tfevents.1704352186.4ce07924bfdd.758.2 +3 -0
  14. logs/text2image-fine-tune/events.out.tfevents.1704352337.4ce07924bfdd.758.4 +3 -0
  15. logs/text2image-fine-tune/events.out.tfevents.1704352528.4ce07924bfdd.758.6 +3 -0
  16. model_index.json +38 -0
  17. safety_checker/config.json +28 -0
  18. safety_checker/model.safetensors +3 -0
  19. scheduler/scheduler_config.json +15 -0
  20. text_encoder/config.json +25 -0
  21. text_encoder/model.safetensors +3 -0
  22. tokenizer/merges.txt +0 -0
  23. tokenizer/special_tokens_map.json +24 -0
  24. tokenizer/tokenizer_config.json +30 -0
  25. tokenizer/vocab.json +0 -0
  26. unet/config.json +68 -0
  27. unet/diffusion_pytorch_model.safetensors +3 -0
  28. vae/config.json +32 -0
  29. vae/diffusion_pytorch_model.safetensors +3 -0
  30. val_imgs_grid.png +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ val_imgs_grid.png filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: creativeml-openrail-m
4
+ base_model: runwayml/stable-diffusion-v1-5
5
+ datasets:
6
+ - lambdalabs/pokemon-blip-captions
7
+ tags:
8
+ - stable-diffusion
9
+ - stable-diffusion-diffusers
10
+ - text-to-image
11
+ - diffusers
12
+ inference: true
13
+ ---
14
+
15
+ # Text-to-image finetuning - shrikant11/pokemon_text_to_image
16
+
17
+ This bla bla pipeline was finetuned from **runwayml/stable-diffusion-v1-5** on the **lambdalabs/pokemon-blip-captions** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['Pokemon with yellow eyes', 'Green colour pokemon', 'Blue colour pikacchu', 'Charlizzard', 'pikachu', 'dangerous looking pokemon']:
18
+
19
+ ![val_imgs_grid](./val_imgs_grid.png)
20
+
21
+
22
+ ## Pipeline usage
23
+
24
+ You can use the pipeline like so:
25
+
26
+ ```python
27
+ from diffusers import DiffusionPipeline
28
+ import torch
29
+
30
+ pipeline = DiffusionPipeline.from_pretrained("shrikant11/pokemon_text_to_image", torch_dtype=torch.float16)
31
+ prompt = "Pokemon with yellow eyes"
32
+ image = pipeline(prompt).images[0]
33
+ image.save("my_image.png")
34
+ ```
35
+
36
+ ## Training info
37
+
38
+ These are the key hyperparameters used during training:
39
+
40
+ * Epochs: 1
41
+ * Learning rate: 1e-05
42
+ * Batch size: 1
43
+ * Gradient accumulation steps: 1
44
+ * Image resolution: 512
45
+ * Mixed-precision: None
46
+
47
+
48
+ More information on all the CLI arguments and the environment are available on your [`wandb` run page]().
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "use_square_size": false
29
+ }
logs/text2image-fine-tune/1704350095.1492045/events.out.tfevents.1704350095.4ce07924bfdd.758.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bc1501e76ac4c7251562532488559311329b6565b832b111cb796b7a7dd92ff
3
+ size 2294
logs/text2image-fine-tune/1704350095.150961/hparams.yml ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 5000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0
21
+ learning_rate: 1.0e-05
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 5001
29
+ mixed_precision: null
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 7
33
+ output_dir: sd-pokemon-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
36
+ pretrained_unet_model_path: text_to_img_1
37
+ push_to_hub: true
38
+ random_flip: true
39
+ report_to: tensorboard
40
+ resolution: 512
41
+ resume_from_checkpoint: null
42
+ revision: null
43
+ scale_lr: false
44
+ seed: null
45
+ snr_gamma: null
46
+ tracker_project_name: text2image-fine-tune
47
+ train_batch_size: 1
48
+ train_data_dir: null
49
+ use_8bit_adam: false
50
+ use_ema: false
51
+ validation_epochs: 5
52
+ variant: null
logs/text2image-fine-tune/1704352186.779532/events.out.tfevents.1704352186.4ce07924bfdd.758.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23dc1e6e15bda15939898cca57f8bc31978a128ca95d6d8be03b1c19075b52e4
3
+ size 2294
logs/text2image-fine-tune/1704352186.7812426/hparams.yml ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 5000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0
21
+ learning_rate: 1.0e-05
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 6
29
+ mixed_precision: null
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-pokemon-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
36
+ pretrained_unet_model_path: text_to_img_1
37
+ push_to_hub: true
38
+ random_flip: true
39
+ report_to: tensorboard
40
+ resolution: 512
41
+ resume_from_checkpoint: null
42
+ revision: null
43
+ scale_lr: false
44
+ seed: null
45
+ snr_gamma: null
46
+ tracker_project_name: text2image-fine-tune
47
+ train_batch_size: 1
48
+ train_data_dir: null
49
+ use_8bit_adam: false
50
+ use_ema: false
51
+ validation_epochs: 5
52
+ variant: null
logs/text2image-fine-tune/1704352337.3800864/events.out.tfevents.1704352337.4ce07924bfdd.758.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92f8c41fb9be7bee4d0a90e3fd764953694bd91bfee80fff69029a445a09f557
3
+ size 2294
logs/text2image-fine-tune/1704352337.3818705/hparams.yml ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 5000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0
21
+ learning_rate: 1.0e-05
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 6
29
+ mixed_precision: null
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-pokemon-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
36
+ pretrained_unet_model_path: text_to_img_1
37
+ push_to_hub: true
38
+ random_flip: true
39
+ report_to: tensorboard
40
+ resolution: 512
41
+ resume_from_checkpoint: null
42
+ revision: null
43
+ scale_lr: false
44
+ seed: null
45
+ snr_gamma: null
46
+ tracker_project_name: text2image-fine-tune
47
+ train_batch_size: 1
48
+ train_data_dir: null
49
+ use_8bit_adam: false
50
+ use_ema: false
51
+ validation_epochs: 5
52
+ variant: null
logs/text2image-fine-tune/1704352528.06429/events.out.tfevents.1704352528.4ce07924bfdd.758.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8751d84dc96cd37670a6ca799679da5f2ad59c106ebf679828f58eec38b58c4c
3
+ size 2294
logs/text2image-fine-tune/1704352528.0660906/hparams.yml ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 5000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0
21
+ learning_rate: 1.0e-05
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 6
29
+ mixed_precision: null
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-pokemon-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
36
+ pretrained_unet_model_path: text_to_img_1
37
+ push_to_hub: true
38
+ random_flip: true
39
+ report_to: tensorboard
40
+ resolution: 512
41
+ resume_from_checkpoint: null
42
+ revision: null
43
+ scale_lr: false
44
+ seed: null
45
+ snr_gamma: null
46
+ tracker_project_name: text2image-fine-tune
47
+ train_batch_size: 1
48
+ train_data_dir: null
49
+ use_8bit_adam: false
50
+ use_ema: false
51
+ validation_epochs: 5
52
+ variant: null
logs/text2image-fine-tune/events.out.tfevents.1704350095.4ce07924bfdd.758.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88f301a3ab9e1f41ac27d36ed858e70ca1158b0ed95748739e84d908f3e09f55
3
+ size 5105749
logs/text2image-fine-tune/events.out.tfevents.1704352186.4ce07924bfdd.758.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b21eea396c75fa2bb08b92b532de3e703d5548057160b2914368de889ff2082
3
+ size 2721712
logs/text2image-fine-tune/events.out.tfevents.1704352337.4ce07924bfdd.758.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:489a8a93515f2dc61e59bb5a73adbb1679a3571b7680325de27f0ea5a63acd05
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1704352528.4ce07924bfdd.758.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d00c85619f31a63cdd20c844fe98d64be5f41e9c2508e4125c904bf831060af5
3
+ size 2351480
model_index.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.25.0",
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": "/root/.cache/huggingface/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": "4.35.2",
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": "0.25.0",
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": "/root/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/1d0c4ebf6ff58a5caecab40fa1406526bca4b5b9/text_encoder",
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": "float32",
23
+ "transformers_version": "4.35.2",
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 sha256:778d02eb9e707c3fbaae0b67b79ea0d1399b52e624fb634f2f19375ae7c047c3
3
+ size 492265168
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": "0.25.0",
4
+ "_name_or_path": "/content/sd-pokemon-model",
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 sha256:2fe25924f819700076ab5073de7dcfaeef76a87258c9e7b6d7da46104df7ec20
3
+ size 3438167536
vae/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.25.0",
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
+ "layers_per_block": 2,
22
+ "norm_num_groups": 32,
23
+ "out_channels": 3,
24
+ "sample_size": 512,
25
+ "scaling_factor": 0.18215,
26
+ "up_block_types": [
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D",
30
+ "UpDecoderBlock2D"
31
+ ]
32
+ }
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
val_imgs_grid.png ADDED

Git LFS Details

  • SHA256: 7d67ad9e67c9f43f09f6bda6b8b1e8e99486dac700a5d8cc360012fe8cd4fb42
  • Pointer size: 132 Bytes
  • Size of remote file: 2.4 MB