rupeshs commited on
Commit
f496aa0
1 Parent(s): 2e4376e

Upload 27 files

Browse files

Added model files

.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
+ unet/openvino_model.xml filter=lfs diff=lfs merge=lfs -text
model_index.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionXLImg2ImgPipeline",
3
+ "_diffusers_version": "0.23.0",
4
+ "_name_or_path": "D:\\om\\2024\\sd\\hypersd\\fastsdcpu\\Hyper-SDXL-1step-lora",
5
+ "force_zeros_for_empty_prompt": true,
6
+ "requires_aesthetics_score": false,
7
+ "scheduler": [
8
+ "diffusers",
9
+ "LCMScheduler"
10
+ ],
11
+ "text_encoder": [
12
+ "transformers",
13
+ "CLIPTextModel"
14
+ ],
15
+ "text_encoder_2": [
16
+ "transformers",
17
+ "CLIPTextModelWithProjection"
18
+ ],
19
+ "tokenizer": [
20
+ "transformers",
21
+ "CLIPTokenizer"
22
+ ],
23
+ "tokenizer_2": [
24
+ "transformers",
25
+ "CLIPTokenizer"
26
+ ],
27
+ "unet": [
28
+ "diffusers",
29
+ "UNet2DConditionModel"
30
+ ],
31
+ "vae": [
32
+ "diffusers",
33
+ "AutoencoderKL"
34
+ ]
35
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "LCMScheduler",
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
+ "interpolation_type": "linear",
11
+ "num_train_timesteps": 1000,
12
+ "original_inference_steps": 50,
13
+ "prediction_type": "epsilon",
14
+ "rescale_betas_zero_snr": false,
15
+ "sample_max_value": 1.0,
16
+ "set_alpha_to_one": false,
17
+ "skip_prk_steps": true,
18
+ "steps_offset": 1,
19
+ "thresholding": false,
20
+ "timestep_scaling": 10.0,
21
+ "timestep_spacing": "leading",
22
+ "trained_betas": null,
23
+ "use_karras_sigmas": false
24
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "D:\\om\\2024\\sd\\hypersd\\fastsdcpu\\Hyper-SDXL-1step-lora\\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
+ "output_hidden_states": true,
21
+ "pad_token_id": 1,
22
+ "projection_dim": 768,
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.34.0",
25
+ "vocab_size": 49408
26
+ }
text_encoder/openvino_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0790ad28ece461644ab0f895ac9512a4b965c942adb63e9a8195b0c3abca437e
3
+ size 124484788
text_encoder/openvino_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
text_encoder_2/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "D:\\om\\2024\\sd\\hypersd\\fastsdcpu\\Hyper-SDXL-1step-lora\\text_encoder_2",
3
+ "architectures": [
4
+ "CLIPTextModelWithProjection"
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": 1280,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 5120,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 20,
19
+ "num_hidden_layers": 32,
20
+ "output_hidden_states": true,
21
+ "pad_token_id": 1,
22
+ "projection_dim": 1280,
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.34.0",
25
+ "vocab_size": 49408
26
+ }
text_encoder_2/openvino_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1b5d60f56bd25f26fa4230db953f08d71308b735aaaec9fd6f491a757f04120
3
+ size 699621056
text_encoder_2/openvino_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 49407,
3
+ "<|startoftext|>": 49406
4
+ }
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 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|startoftext|>",
4
+ "<|endoftext|>"
5
+ ],
6
+ "bos_token": "<|startoftext|>",
7
+ "eos_token": "<|endoftext|>",
8
+ "pad_token": "<|endoftext|>",
9
+ "unk_token": "<|endoftext|>"
10
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "49406": {
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49407": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "additional_special_tokens": [
22
+ "<|startoftext|>",
23
+ "<|endoftext|>"
24
+ ],
25
+ "bos_token": "<|startoftext|>",
26
+ "clean_up_tokenization_spaces": true,
27
+ "do_lower_case": true,
28
+ "eos_token": "<|endoftext|>",
29
+ "errors": "replace",
30
+ "model_max_length": 77,
31
+ "pad_token": "<|endoftext|>",
32
+ "tokenizer_class": "CLIPTokenizer",
33
+ "tokenizer_file": null,
34
+ "unk_token": "<|endoftext|>"
35
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_2/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "!": 0,
3
+ "<|endoftext|>": 49407,
4
+ "<|startoftext|>": 49406
5
+ }
tokenizer_2/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_2/special_tokens_map.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "!",
4
+ "<|startoftext|>",
5
+ "<|endoftext|>"
6
+ ],
7
+ "bos_token": "<|startoftext|>",
8
+ "eos_token": "<|endoftext|>",
9
+ "pad_token": "!",
10
+ "unk_token": "<|endoftext|>"
11
+ }
tokenizer_2/tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "!",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49406": {
13
+ "content": "<|startoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "49407": {
21
+ "content": "<|endoftext|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "!",
31
+ "<|startoftext|>",
32
+ "<|endoftext|>"
33
+ ],
34
+ "bos_token": "<|startoftext|>",
35
+ "clean_up_tokenization_spaces": true,
36
+ "do_lower_case": true,
37
+ "eos_token": "<|endoftext|>",
38
+ "errors": "replace",
39
+ "model_max_length": 77,
40
+ "pad_token": "!",
41
+ "tokenizer_class": "CLIPTokenizer",
42
+ "tokenizer_file": null,
43
+ "unk_token": "<|endoftext|>"
44
+ }
tokenizer_2/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.23.0",
4
+ "_name_or_path": "D:\\om\\2024\\sd\\hypersd\\fastsdcpu\\Hyper-SDXL-1step-lora\\unet",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": "text_time",
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": 256,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20
13
+ ],
14
+ "attention_type": "default",
15
+ "block_out_channels": [
16
+ 320,
17
+ 640,
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": 2048,
26
+ "cross_attention_norm": null,
27
+ "down_block_types": [
28
+ "DownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D"
31
+ ],
32
+ "downsample_padding": 1,
33
+ "dropout": 0.0,
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_attention_heads": null,
47
+ "num_class_embeds": null,
48
+ "only_cross_attention": false,
49
+ "out_channels": 4,
50
+ "projection_class_embeddings_input_dim": 2816,
51
+ "resnet_out_scale_factor": 1.0,
52
+ "resnet_skip_time_act": false,
53
+ "resnet_time_scale_shift": "default",
54
+ "reverse_transformer_layers_per_block": null,
55
+ "sample_size": 128,
56
+ "time_cond_proj_dim": null,
57
+ "time_embedding_act_fn": null,
58
+ "time_embedding_dim": null,
59
+ "time_embedding_type": "positional",
60
+ "timestep_post_act": null,
61
+ "transformer_layers_per_block": [
62
+ 1,
63
+ 2,
64
+ 10
65
+ ],
66
+ "up_block_types": [
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "UpBlock2D"
70
+ ],
71
+ "upcast_attention": null,
72
+ "use_linear_projection": true
73
+ }
unet/openvino_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34c45c9e250606a20733fb3dc8e6d79a0f4b867ca06f34ff99134eaefdc1a724
3
+ size 3583553376
unet/openvino_model.xml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3daa909ac7fa712c8b8d01b51ab1388eba8bbae2c998e0b91a5c4afbf7e6f10
3
+ size 12715145
vae_decoder/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.23.0",
4
+ "_name_or_path": "D:\\om\\2024\\sd\\hypersd\\fastsdcpu\\Hyper-SDXL-1step-lora\\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
+ "latents_mean": null,
22
+ "latents_std": null,
23
+ "layers_per_block": 2,
24
+ "norm_num_groups": 32,
25
+ "out_channels": 3,
26
+ "sample_size": 1024,
27
+ "scaling_factor": 0.13025,
28
+ "up_block_types": [
29
+ "UpDecoderBlock2D",
30
+ "UpDecoderBlock2D",
31
+ "UpDecoderBlock2D",
32
+ "UpDecoderBlock2D"
33
+ ]
34
+ }
vae_decoder/openvino_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5d481f233a0e11fe604195814c200b8f98694f42ace08848c0f289ac793c47b
3
+ size 194831588
vae_decoder/openvino_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
vae_encoder/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.23.0",
4
+ "_name_or_path": "D:\\om\\2024\\sd\\hypersd\\fastsdcpu\\Hyper-SDXL-1step-lora\\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
+ "latents_mean": null,
22
+ "latents_std": null,
23
+ "layers_per_block": 2,
24
+ "norm_num_groups": 32,
25
+ "out_channels": 3,
26
+ "sample_size": 1024,
27
+ "scaling_factor": 0.13025,
28
+ "up_block_types": [
29
+ "UpDecoderBlock2D",
30
+ "UpDecoderBlock2D",
31
+ "UpDecoderBlock2D",
32
+ "UpDecoderBlock2D"
33
+ ]
34
+ }
vae_encoder/openvino_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4121bcc335dc7909e48e6ba6dcfd922bc2984221f11d5a238bd6c1309058f4ff
3
+ size 133525452
vae_encoder/openvino_model.xml ADDED
The diff for this file is too large to render. See raw diff