JoPmt commited on
Commit
98dba43
·
verified ·
1 Parent(s): 01a9a90

Upload StableDiffusionPipeline

Browse files
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPFeatureExtractor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 224
26
+ }
27
+ }
model_index.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.23.0",
4
+ "_name_or_path": "stablediffusionapi/edge-of-realism",
5
+ "feature_extractor": [
6
+ "transformers",
7
+ "CLIPFeatureExtractor"
8
+ ],
9
+ "requires_safety_checker": true,
10
+ "safety_checker": [
11
+ null,
12
+ null
13
+ ],
14
+ "scheduler": [
15
+ "diffusers",
16
+ "PNDMScheduler"
17
+ ],
18
+ "text_encoder": [
19
+ "transformers",
20
+ "CLIPTextModel"
21
+ ],
22
+ "tokenizer": [
23
+ "transformers",
24
+ "CLIPTokenizer"
25
+ ],
26
+ "unet": [
27
+ "diffusers",
28
+ "UNet2DConditionModel"
29
+ ],
30
+ "vae": [
31
+ "diffusers",
32
+ "AutoencoderKL"
33
+ ]
34
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.23.0",
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": "epsilon",
12
+ "sample_max_value": 1.0,
13
+ "set_alpha_to_one": false,
14
+ "skip_prk_steps": true,
15
+ "steps_offset": 1,
16
+ "thresholding": false,
17
+ "timestep_spacing": "leading",
18
+ "trained_betas": null
19
+ }
text_encoder/adapter_config.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": null,
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": false,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 64.0,
13
+ "lora_dropout": 0.0,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 128,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "text_model.encoder.layers.0.self_attn.k_proj",
23
+ "text_model.encoder.layers.8.self_attn.out_proj",
24
+ "text_model.encoder.layers.8.self_attn.q_proj",
25
+ "text_model.encoder.layers.3.mlp.fc2",
26
+ "text_model.encoder.layers.0.self_attn.v_proj",
27
+ "text_model.encoder.layers.9.self_attn.q_proj",
28
+ "text_model.encoder.layers.8.mlp.fc2",
29
+ "text_model.encoder.layers.2.self_attn.q_proj",
30
+ "text_model.encoder.layers.11.self_attn.k_proj",
31
+ "text_model.encoder.layers.5.self_attn.v_proj",
32
+ "text_model.encoder.layers.6.self_attn.out_proj",
33
+ "text_model.encoder.layers.3.self_attn.q_proj",
34
+ "text_model.encoder.layers.3.mlp.fc1",
35
+ "text_model.encoder.layers.7.self_attn.k_proj",
36
+ "text_model.encoder.layers.10.self_attn.q_proj",
37
+ "text_model.encoder.layers.7.mlp.fc1",
38
+ "text_model.encoder.layers.6.mlp.fc2",
39
+ "text_model.encoder.layers.9.self_attn.k_proj",
40
+ "text_model.encoder.layers.2.self_attn.out_proj",
41
+ "text_model.encoder.layers.2.mlp.fc2",
42
+ "text_model.encoder.layers.4.mlp.fc1",
43
+ "text_model.encoder.layers.8.self_attn.v_proj",
44
+ "text_model.encoder.layers.5.self_attn.out_proj",
45
+ "text_model.encoder.layers.6.self_attn.q_proj",
46
+ "text_model.encoder.layers.6.self_attn.v_proj",
47
+ "text_model.encoder.layers.0.mlp.fc2",
48
+ "text_model.encoder.layers.2.self_attn.v_proj",
49
+ "text_model.encoder.layers.9.self_attn.out_proj",
50
+ "text_model.encoder.layers.6.mlp.fc1",
51
+ "text_model.encoder.layers.9.mlp.fc1",
52
+ "text_model.encoder.layers.7.mlp.fc2",
53
+ "text_model.encoder.layers.4.mlp.fc2",
54
+ "text_model.encoder.layers.11.mlp.fc2",
55
+ "text_model.encoder.layers.5.self_attn.q_proj",
56
+ "text_model.encoder.layers.5.mlp.fc2",
57
+ "text_model.encoder.layers.0.self_attn.q_proj",
58
+ "text_model.encoder.layers.1.mlp.fc2",
59
+ "text_model.encoder.layers.2.self_attn.k_proj",
60
+ "text_model.encoder.layers.11.mlp.fc1",
61
+ "text_model.encoder.layers.4.self_attn.out_proj",
62
+ "text_model.encoder.layers.10.self_attn.k_proj",
63
+ "text_model.encoder.layers.10.self_attn.v_proj",
64
+ "text_model.encoder.layers.6.self_attn.k_proj",
65
+ "text_model.encoder.layers.5.mlp.fc1",
66
+ "text_model.encoder.layers.10.mlp.fc2",
67
+ "text_model.encoder.layers.7.self_attn.v_proj",
68
+ "text_model.encoder.layers.9.self_attn.v_proj",
69
+ "text_model.encoder.layers.8.self_attn.k_proj",
70
+ "text_model.encoder.layers.11.self_attn.out_proj",
71
+ "text_model.encoder.layers.1.self_attn.out_proj",
72
+ "text_model.encoder.layers.3.self_attn.k_proj",
73
+ "text_model.encoder.layers.1.self_attn.q_proj",
74
+ "text_model.encoder.layers.2.mlp.fc1",
75
+ "text_model.encoder.layers.9.mlp.fc2",
76
+ "text_model.encoder.layers.3.self_attn.v_proj",
77
+ "text_model.encoder.layers.11.self_attn.q_proj",
78
+ "text_model.encoder.layers.3.self_attn.out_proj",
79
+ "text_model.encoder.layers.1.self_attn.k_proj",
80
+ "text_model.encoder.layers.5.self_attn.k_proj",
81
+ "text_model.encoder.layers.0.self_attn.out_proj",
82
+ "text_model.encoder.layers.10.self_attn.out_proj",
83
+ "text_model.encoder.layers.4.self_attn.q_proj",
84
+ "text_model.encoder.layers.0.mlp.fc1",
85
+ "text_model.encoder.layers.4.self_attn.v_proj",
86
+ "text_model.encoder.layers.7.self_attn.out_proj",
87
+ "text_model.encoder.layers.1.self_attn.v_proj",
88
+ "text_model.encoder.layers.8.mlp.fc1",
89
+ "text_model.encoder.layers.10.mlp.fc1",
90
+ "text_model.encoder.layers.1.mlp.fc1",
91
+ "text_model.encoder.layers.7.self_attn.q_proj",
92
+ "text_model.encoder.layers.4.self_attn.k_proj",
93
+ "text_model.encoder.layers.11.self_attn.v_proj"
94
+ ],
95
+ "task_type": null,
96
+ "use_dora": false,
97
+ "use_rslora": false
98
+ }
text_encoder/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dff0c8f249dc882eb99641d515a98b4533d8a4998768d0b11161a8fcc39e13a2
3
+ size 42488272
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": "0.23.0",
4
+ "_name_or_path": "/home/user/.cache/huggingface/hub/models--stablediffusionapi--edge-of-realism/snapshots/e9ae5202176cd3d3039b2ea150ec5e703099bc35/unet",
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 sha256:33c8f497002d6cabc2a7ec7f144a0ebe7bdbbfd233dc2b68e70f95a39246bde9
3
+ size 1936298600
vae/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.23.0",
4
+ "_name_or_path": "/home/user/.cache/huggingface/hub/models--stablediffusionapi--edge-of-realism/snapshots/e9ae5202176cd3d3039b2ea150ec5e703099bc35/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
+ "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:b098a5344a351d15c60d5db05875b305c3a79005e144881dfeab9e2670f42ccc
3
+ size 167335590