mekrod commited on
Commit
5f598d0
1 Parent(s): 8d9af1c

Upload with huggingface_hub

Browse files
args.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "shuffle_per_epoch": false,
3
+ "attention": "xformers",
4
+ "model_variant": "base",
5
+ "aspect_mode": "dynamic",
6
+ "aspect_mode_action_preference": "add",
7
+ "use_ema": true,
8
+ "clip_penultimate": false,
9
+ "conditional_dropout": null,
10
+ "disable_cudnn_benchmark": true,
11
+ "use_text_files_as_captions": false,
12
+ "sample_from_batch": 0,
13
+ "stop_text_encoder_training": 999999999999999,
14
+ "use_bucketing": true,
15
+ "regenerate_latent_cache": true,
16
+ "sample_on_training_start": true,
17
+ "add_class_images_to_dataset": false,
18
+ "auto_balance_concept_datasets": false,
19
+ "sample_aspect_ratios": false,
20
+ "dataset_repeats": 1,
21
+ "save_every_n_epoch": 5,
22
+ "pretrained_model_name_or_path": "mekrod/vmp1",
23
+ "pretrained_vae_name_or_path": "input_vae_model/VAE",
24
+ "tokenizer_name": null,
25
+ "instance_data_dir": null,
26
+ "class_data_dir": null,
27
+ "instance_prompt": null,
28
+ "class_prompt": null,
29
+ "save_sample_prompt": null,
30
+ "n_save_sample": 1,
31
+ "sample_height": 512,
32
+ "sample_width": 512,
33
+ "save_guidance_scale": 7.5,
34
+ "save_infer_steps": 30,
35
+ "with_prior_preservation": false,
36
+ "prior_loss_weight": 1.0,
37
+ "num_class_images": 206,
38
+ "output_dir": "output/vmp1e",
39
+ "seed": 3534554,
40
+ "resolution": 512,
41
+ "center_crop": false,
42
+ "train_text_encoder": false,
43
+ "train_batch_size": 1,
44
+ "sample_batch_size": 4,
45
+ "num_train_epochs": 20,
46
+ "max_train_steps": 1140,
47
+ "gradient_accumulation_steps": 1,
48
+ "gradient_checkpointing": true,
49
+ "learning_rate": 1e-06,
50
+ "scale_lr": false,
51
+ "lr_scheduler": "constant",
52
+ "lr_warmup_steps": 0,
53
+ "use_8bit_adam": true,
54
+ "adam_beta1": 0.9,
55
+ "adam_beta2": 0.999,
56
+ "adam_weight_decay": 0.01,
57
+ "adam_epsilon": 1e-08,
58
+ "max_grad_norm": 1.0,
59
+ "push_to_hub": false,
60
+ "hub_token": null,
61
+ "hub_model_id": null,
62
+ "logging_dir": "logs",
63
+ "log_interval": 10,
64
+ "sample_step_interval": 500,
65
+ "mixed_precision": "fp16",
66
+ "local_rank": -1,
67
+ "concepts_list": [
68
+ {
69
+ "instance_prompt": "Magali Villeneuve",
70
+ "instance_data_dir": "datasets/Magali Villeneuve",
71
+ "class_prompt": "",
72
+ "class_data_dir": "",
73
+ "do_not_balance": 0,
74
+ "use_sub_dirs": 0
75
+ },
76
+ {
77
+ "instance_prompt": "Bo Chen",
78
+ "instance_data_dir": "datasets/Bo Chen",
79
+ "class_prompt": "",
80
+ "class_data_dir": "",
81
+ "do_not_balance": 0,
82
+ "use_sub_dirs": 0
83
+ },
84
+ {
85
+ "instance_prompt": "Chengwei Pan",
86
+ "instance_data_dir": "datasets/Chengwei Pan",
87
+ "class_prompt": "",
88
+ "class_data_dir": "",
89
+ "do_not_balance": 0,
90
+ "use_sub_dirs": 0
91
+ }
92
+ ],
93
+ "save_sample_controlled_seed": null,
94
+ "detect_full_drive": true,
95
+ "send_telegram_updates": false,
96
+ "telegram_chat_id": "0",
97
+ "telegram_token": "0",
98
+ "use_deepspeed_adam": false,
99
+ "append_sample_controlled_seed_action": null,
100
+ "add_sample_prompt": null,
101
+ "use_image_names_as_captions": true,
102
+ "mask_prompts": null,
103
+ "batch_tokens": null
104
+ }
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
+ }
model_index.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.10.2",
4
+ "feature_extractor": [
5
+ "transformers",
6
+ "CLIPImageProcessor"
7
+ ],
8
+ "requires_safety_checker": true,
9
+ "safety_checker": [
10
+ null,
11
+ null
12
+ ],
13
+ "scheduler": [
14
+ "diffusers",
15
+ "PNDMScheduler"
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 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DPMSolverMultistepScheduler",
3
+ "_diffusers_version": "0.10.2",
4
+ "algorithm_type": "dpmsolver++",
5
+ "beta_end": 0.012,
6
+ "beta_schedule": "scaled_linear",
7
+ "beta_start": 0.00085,
8
+ "clip_sample": false,
9
+ "dynamic_thresholding_ratio": 0.995,
10
+ "lower_order_final": true,
11
+ "num_train_timesteps": 1000,
12
+ "prediction_type": "epsilon",
13
+ "sample_max_value": 1.0,
14
+ "set_alpha_to_one": false,
15
+ "skip_prk_steps": true,
16
+ "solver_order": 2,
17
+ "solver_type": "midpoint",
18
+ "steps_offset": 1,
19
+ "thresholding": false,
20
+ "trained_betas": null
21
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mekrod/vmp1",
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": "4.25.1",
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:fd12d8b6f52dd17cfd35baf3c5c1f229467ba930658b80301668707b74a042f5
3
+ size 492265879
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 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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--mekrod--vmp1/snapshots/6d5743b2b92916b33a6aec071ca54ff8f0b6cd09/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 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.10.2",
4
+ "_name_or_path": "mekrod/vmp1",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": 8,
7
+ "block_out_channels": [
8
+ 320,
9
+ 640,
10
+ 1280,
11
+ 1280
12
+ ],
13
+ "center_input_sample": false,
14
+ "class_embed_type": null,
15
+ "cross_attention_dim": 768,
16
+ "down_block_types": [
17
+ "CrossAttnDownBlock2D",
18
+ "CrossAttnDownBlock2D",
19
+ "CrossAttnDownBlock2D",
20
+ "DownBlock2D"
21
+ ],
22
+ "downsample_padding": 1,
23
+ "dual_cross_attention": false,
24
+ "flip_sin_to_cos": true,
25
+ "freq_shift": 0,
26
+ "in_channels": 4,
27
+ "layers_per_block": 2,
28
+ "mid_block_scale_factor": 1,
29
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
30
+ "norm_eps": 1e-05,
31
+ "norm_num_groups": 32,
32
+ "num_class_embeds": null,
33
+ "only_cross_attention": false,
34
+ "out_channels": 4,
35
+ "resnet_time_scale_shift": "default",
36
+ "sample_size": 64,
37
+ "up_block_types": [
38
+ "UpBlock2D",
39
+ "CrossAttnUpBlock2D",
40
+ "CrossAttnUpBlock2D",
41
+ "CrossAttnUpBlock2D"
42
+ ],
43
+ "upcast_attention": false,
44
+ "use_linear_projection": false
45
+ }
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8f2c9182812e72b40e016088f36a4cbd4b80c8a19a3908d27b34536ae49a1c6
3
+ size 3438167503
vae/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.10.2",
4
+ "_name_or_path": "input_vae_model/VAE",
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
+ "up_block_types": [
25
+ "UpDecoderBlock2D",
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D"
29
+ ]
30
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beac981a8939a0430dd9b71027125d6abe863f8667f0d8497b9e2f6aa9a1db80
3
+ size 334643245