Hugging Face's logo

Dipl0
/
pepe-diffuser

Text-to-Image
Diffusers
TensorBoard
StableDiffusionPipeline
pepe
Inference Endpoints
Model card Files Metrics Community
Dipl0 commited on
Commit
948253b
•
1 Parent(s): 9ad2360

first commit

Browse files
Files changed (22) hide show
  1. feature_extractor/preprocessor_config.json +28 -0
  2. logs/text2image-fine-tune/1675706489.2034416/events.out.tfevents.1675706489.4fe00372c4ff.937.1 +3 -0
  3. logs/text2image-fine-tune/1675706489.2044406/hparams.yml +43 -0
  4. logs/text2image-fine-tune/1675706858.9182036/events.out.tfevents.1675706858.4fe00372c4ff.1051.1 +3 -0
  5. logs/text2image-fine-tune/1675706858.9191566/hparams.yml +43 -0
  6. logs/text2image-fine-tune/1675706998.692587/events.out.tfevents.1675706998.4fe00372c4ff.1158.1 +3 -0
  7. logs/text2image-fine-tune/1675706998.6936088/hparams.yml +43 -0
  8. logs/text2image-fine-tune/events.out.tfevents.1675706489.4fe00372c4ff.937.0 +3 -0
  9. logs/text2image-fine-tune/events.out.tfevents.1675706858.4fe00372c4ff.1051.0 +3 -0
  10. logs/text2image-fine-tune/events.out.tfevents.1675706998.4fe00372c4ff.1158.0 +3 -0
  11. model_index.json +33 -0
  12. scheduler/scheduler_config.json +14 -0
  13. text_encoder/config.json +25 -0
  14. text_encoder/pytorch_model.bin +3 -0
  15. tokenizer/merges.txt +0 -0
  16. tokenizer/special_tokens_map.json +24 -0
  17. tokenizer/tokenizer_config.json +34 -0
  18. tokenizer/vocab.json +0 -0
  19. unet/config.json +50 -0
  20. unet/diffusion_pytorch_model.bin +3 -0
  21. vae/config.json +31 -0
  22. vae/diffusion_pytorch_model.bin +3 -0
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": "CLIPFeatureExtractor",
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
+ }
logs/text2image-fine-tune/1675706489.2034416/events.out.tfevents.1675706489.4fe00372c4ff.937.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df2acf9239f954287010875c1bdd49e7071e17c9fee865aeeff310708a101182
3
+ size 1902
logs/text2image-fine-tune/1675706489.2044406/hparams.yml ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 10000
10
+ dataloader_num_workers: 0
11
+ dataset_config_name: null
12
+ dataset_name: null
13
+ enable_xformers_memory_efficient_attention: false
14
+ gradient_accumulation_steps: 4
15
+ gradient_checkpointing: true
16
+ hub_model_id: null
17
+ hub_token: null
18
+ image_column: image
19
+ learning_rate: 1.0e-05
20
+ local_rank: -1
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 0
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 15000
27
+ mixed_precision: null
28
+ non_ema_revision: null
29
+ num_train_epochs: 13
30
+ output_dir: pepe_model
31
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2
32
+ push_to_hub: false
33
+ random_flip: true
34
+ report_to: tensorboard
35
+ resolution: 768
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ scale_lr: false
39
+ seed: null
40
+ train_batch_size: 1
41
+ train_data_dir: ''
42
+ use_8bit_adam: false
43
+ use_ema: true
logs/text2image-fine-tune/1675706858.9182036/events.out.tfevents.1675706858.4fe00372c4ff.1051.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f86138352ee96aa430047556512642bbcd15d06d24843498b6514e3e9cb4296
3
+ size 1901
logs/text2image-fine-tune/1675706858.9191566/hparams.yml ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 10000
10
+ dataloader_num_workers: 0
11
+ dataset_config_name: null
12
+ dataset_name: null
13
+ enable_xformers_memory_efficient_attention: false
14
+ gradient_accumulation_steps: 4
15
+ gradient_checkpointing: true
16
+ hub_model_id: null
17
+ hub_token: null
18
+ image_column: image
19
+ learning_rate: 1.0e-05
20
+ local_rank: -1
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 0
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 15000
27
+ mixed_precision: null
28
+ non_ema_revision: null
29
+ num_train_epochs: 13
30
+ output_dir: pepe_model
31
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
32
+ push_to_hub: false
33
+ random_flip: true
34
+ report_to: tensorboard
35
+ resolution: 768
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ scale_lr: false
39
+ seed: null
40
+ train_batch_size: 1
41
+ train_data_dir: ''
42
+ use_8bit_adam: false
43
+ use_ema: true
logs/text2image-fine-tune/1675706998.692587/events.out.tfevents.1675706998.4fe00372c4ff.1158.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14e0c275b340a02e2e5e508c623e51b128dc266f5eb39d884d7238f7d3d8839b
3
+ size 1902
logs/text2image-fine-tune/1675706998.6936088/hparams.yml ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 10000
10
+ dataloader_num_workers: 0
11
+ dataset_config_name: null
12
+ dataset_name: null
13
+ enable_xformers_memory_efficient_attention: false
14
+ gradient_accumulation_steps: 4
15
+ gradient_checkpointing: true
16
+ hub_model_id: null
17
+ hub_token: null
18
+ image_column: image
19
+ learning_rate: 1.0e-05
20
+ local_rank: -1
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 0
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 15000
27
+ mixed_precision: null
28
+ non_ema_revision: null
29
+ num_train_epochs: 13
30
+ output_dir: pepe_model
31
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2
32
+ push_to_hub: false
33
+ random_flip: true
34
+ report_to: tensorboard
35
+ resolution: 768
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ scale_lr: false
39
+ seed: null
40
+ train_batch_size: 1
41
+ train_data_dir: ''
42
+ use_8bit_adam: false
43
+ use_ema: true
logs/text2image-fine-tune/events.out.tfevents.1675706489.4fe00372c4ff.937.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6050c89e71401b67a5c432cf5c15a6a975a73463024158a7bf7ae73a6097eef5
3
+ size 3304
logs/text2image-fine-tune/events.out.tfevents.1675706858.4fe00372c4ff.1051.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:043457a6cec5d6f3241ac53f4740b88687604ac1b768e2a8f2ae50d7fef8374b
3
+ size 808
logs/text2image-fine-tune/events.out.tfevents.1675706998.4fe00372c4ff.1158.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e01959245446e8778ea693af030492bf5a153e71fbbc3ba74cce1f9da77f8038
3
+ size 734913
model_index.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.13.0.dev0",
4
+ "feature_extractor": [
5
+ "transformers",
6
+ "CLIPFeatureExtractor"
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 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDIMScheduler",
3
+ "_diffusers_version": "0.13.0.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": "v_prediction",
10
+ "set_alpha_to_one": false,
11
+ "skip_prk_steps": true,
12
+ "steps_offset": 1,
13
+ "trained_betas": null
14
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "stabilityai/stable-diffusion-2",
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": "float16",
23
+ "transformers_version": "4.26.0",
24
+ "vocab_size": 49408
25
+ }
text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2a06cf32cf585d03b55fef302142a5321b761ec440113925f64f4ceaffc7730
3
+ size 680904225
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 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "do_lower_case": true,
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 77,
22
+ "name_or_path": "/root/.cache/huggingface/diffusers/models--stabilityai--stable-diffusion-2/snapshots/07753ec23aeaf08862a5f6a8fcb0f9a883863b1b/tokenizer",
23
+ "pad_token": "<|endoftext|>",
24
+ "special_tokens_map_file": "./special_tokens_map.json",
25
+ "tokenizer_class": "CLIPTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.13.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": [
7
+ 5,
8
+ 10,
9
+ 20,
10
+ 20
11
+ ],
12
+ "block_out_channels": [
13
+ 320,
14
+ 640,
15
+ 1280,
16
+ 1280
17
+ ],
18
+ "center_input_sample": false,
19
+ "class_embed_type": null,
20
+ "cross_attention_dim": 1024,
21
+ "down_block_types": [
22
+ "CrossAttnDownBlock2D",
23
+ "CrossAttnDownBlock2D",
24
+ "CrossAttnDownBlock2D",
25
+ "DownBlock2D"
26
+ ],
27
+ "downsample_padding": 1,
28
+ "dual_cross_attention": false,
29
+ "flip_sin_to_cos": true,
30
+ "freq_shift": 0,
31
+ "in_channels": 4,
32
+ "layers_per_block": 2,
33
+ "mid_block_scale_factor": 1,
34
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
35
+ "norm_eps": 1e-05,
36
+ "norm_num_groups": 32,
37
+ "num_class_embeds": null,
38
+ "only_cross_attention": false,
39
+ "out_channels": 4,
40
+ "resnet_time_scale_shift": "default",
41
+ "sample_size": 96,
42
+ "up_block_types": [
43
+ "UpBlock2D",
44
+ "CrossAttnUpBlock2D",
45
+ "CrossAttnUpBlock2D",
46
+ "CrossAttnUpBlock2D"
47
+ ],
48
+ "upcast_attention": false,
49
+ "use_linear_projection": true
50
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7cacf554de4cf0efa56b83e91c1cf6d63b4314633b206e502507e6cfa4e3335
3
+ size 3463934693
vae/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.13.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2",
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 sha256:11bc15ceb385823b4adb68bd5bdd7568d0c706c3de5ea9ebcb0b807092fc9030
3
+ size 167407601