Hugging Face's logo

RunDiffusion
/
Juggernaut-X-Hyper

Text-to-Image
Diffusers
English
StableDiffusionXLPipeline
art
people
diffusion
Cinematic
Photography
Landscape
Interior
Food
Car
Wildlife
Architecture
Inference Endpoints
Model card Files Community
3

Adding `diffusers` weights of this model

#3
by MorpheusXX0 - opened
base: refs/heads/main
←
from: refs/pr/3
Discussion Files changed
+196928
-196937
Files changed (24) hide show
  1. model_index.json +33 -41
  2. scheduler/scheduler_config.json +18 -21
  3. text_encoder/config.json +24 -24
  4. text_encoder/model.fp16.safetensors +3 -0
  5. text_encoder/model.safetensors +3 -0
  6. text_encoder_2/config.json +24 -24
  7. text_encoder_2/model.fp16.safetensors +3 -0
  8. text_encoder_2/model.safetensors +3 -0
  9. tokenizer/added_tokens.json +4 -0
  10. tokenizer/merges.txt +0 -0
  11. tokenizer/special_tokens_map.json +6 -24
  12. tokenizer/tokenizer_config.json +32 -33
  13. tokenizer/vocab.json +0 -0
  14. tokenizer_2/added_tokens.json +5 -0
  15. tokenizer_2/merges.txt +0 -0
  16. tokenizer_2/special_tokens_map.json +6 -24
  17. tokenizer_2/tokenizer_config.json +40 -33
  18. tokenizer_2/vocab.json +0 -0
  19. unet/config.json +71 -72
  20. unet/diffusion_pytorch_model.fp16.safetensors +3 -0
  21. unet/diffusion_pytorch_model.safetensors +3 -0
  22. vae/config.json +31 -31
  23. vae/diffusion_pytorch_model.fp16.safetensors +3 -0
  24. vae/diffusion_pytorch_model.safetensors +3 -0
model_index.json CHANGED
@@ -1,41 +1,33 @@
1
- {
2
- "_class_name": "StableDiffusionXLPipeline",
3
- "_diffusers_version": "0.26.3",
4
- "feature_extractor": [
5
- null,
6
- null
7
- ],
8
- "force_zeros_for_empty_prompt": true,
9
- "image_encoder": [
10
- null,
11
- null
12
- ],
13
- "scheduler": [
14
- "diffusers",
15
- "EulerDiscreteScheduler"
16
- ],
17
- "text_encoder": [
18
- "transformers",
19
- "CLIPTextModel"
20
- ],
21
- "text_encoder_2": [
22
- "transformers",
23
- "CLIPTextModelWithProjection"
24
- ],
25
- "tokenizer": [
26
- "transformers",
27
- "CLIPTokenizer"
28
- ],
29
- "tokenizer_2": [
30
- "transformers",
31
- "CLIPTokenizer"
32
- ],
33
- "unet": [
34
- "diffusers",
35
- "UNet2DConditionModel"
36
- ],
37
- "vae": [
38
- "diffusers",
39
- "AutoencoderKL"
40
- ]
41
- }
 
1
+ {
2
+ "_class_name": "StableDiffusionXLPipeline",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "force_zeros_for_empty_prompt": true,
5
+ "scheduler": [
6
+ "diffusers",
7
+ "EulerDiscreteScheduler"
8
+ ],
9
+ "text_encoder": [
10
+ "transformers",
11
+ "CLIPTextModel"
12
+ ],
13
+ "text_encoder_2": [
14
+ "transformers",
15
+ "CLIPTextModelWithProjection"
16
+ ],
17
+ "tokenizer": [
18
+ "transformers",
19
+ "CLIPTokenizer"
20
+ ],
21
+ "tokenizer_2": [
22
+ "transformers",
23
+ "CLIPTokenizer"
24
+ ],
25
+ "unet": [
26
+ "diffusers",
27
+ "UNet2DConditionModel"
28
+ ],
29
+ "vae": [
30
+ "diffusers",
31
+ "AutoencoderKL"
32
+ ]
33
+ }
 
 
 
 
 
 
 
 
scheduler/scheduler_config.json CHANGED
@@ -1,21 +1,18 @@
1
- {
2
- "_class_name": "EulerDiscreteScheduler",
3
- "_diffusers_version": "0.26.3",
4
- "beta_end": 0.012,
5
- "beta_schedule": "scaled_linear",
6
- "beta_start": 0.00085,
7
- "interpolation_type": "linear",
8
- "num_train_timesteps": 1000,
9
- "prediction_type": "epsilon",
10
- "rescale_betas_zero_snr": false,
11
- "sample_max_value": 1.0,
12
- "set_alpha_to_one": false,
13
- "sigma_max": null,
14
- "sigma_min": null,
15
- "skip_prk_steps": true,
16
- "steps_offset": 1,
17
- "timestep_spacing": "leading",
18
- "timestep_type": "discrete",
19
- "trained_betas": null,
20
- "use_karras_sigmas": false
21
- }
 
1
+ {
2
+ "_class_name": "EulerDiscreteScheduler",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "interpolation_type": "linear",
9
+ "num_train_timesteps": 1000,
10
+ "prediction_type": "epsilon",
11
+ "sample_max_value": 1.0,
12
+ "set_alpha_to_one": false,
13
+ "skip_prk_steps": true,
14
+ "steps_offset": 1,
15
+ "timestep_spacing": "leading",
16
+ "trained_betas": null,
17
+ "use_karras_sigmas": false
18
+ }
 
 
 
text_encoder/config.json CHANGED
@@ -1,24 +1,24 @@
1
- {
2
- "architectures": [
3
- "CLIPTextModel"
4
- ],
5
- "attention_dropout": 0.0,
6
- "bos_token_id": 0,
7
- "dropout": 0.0,
8
- "eos_token_id": 2,
9
- "hidden_act": "quick_gelu",
10
- "hidden_size": 768,
11
- "initializer_factor": 1.0,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 3072,
14
- "layer_norm_eps": 1e-05,
15
- "max_position_embeddings": 77,
16
- "model_type": "clip_text_model",
17
- "num_attention_heads": 12,
18
- "num_hidden_layers": 12,
19
- "pad_token_id": 1,
20
- "projection_dim": 768,
21
- "torch_dtype": "float32",
22
- "transformers_version": "4.30.2",
23
- "vocab_size": 49408
24
- }
 
1
+ {
2
+ "architectures": [
3
+ "CLIPTextModel"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 0,
7
+ "dropout": 0.0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "quick_gelu",
10
+ "hidden_size": 768,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 77,
16
+ "model_type": "clip_text_model",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "projection_dim": 768,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.34.0",
23
+ "vocab_size": 49408
24
+ }
text_encoder/model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfb785e8fe528582de365a33fe34806630e9b5173dbe93101b9d3f913cb72832
3
+ size 246144152
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f623bef6cb72ce6e3927fcb3c04b524d8f06a901d8d323d14bed0b924f058b96
3
+ size 492265168
text_encoder_2/config.json CHANGED
@@ -1,24 +1,24 @@
1
- {
2
- "architectures": [
3
- "CLIPTextModelWithProjection"
4
- ],
5
- "attention_dropout": 0.0,
6
- "bos_token_id": 0,
7
- "dropout": 0.0,
8
- "eos_token_id": 2,
9
- "hidden_act": "gelu",
10
- "hidden_size": 1280,
11
- "initializer_factor": 1.0,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 5120,
14
- "layer_norm_eps": 1e-05,
15
- "max_position_embeddings": 77,
16
- "model_type": "clip_text_model",
17
- "num_attention_heads": 20,
18
- "num_hidden_layers": 32,
19
- "pad_token_id": 1,
20
- "projection_dim": 1280,
21
- "torch_dtype": "float32",
22
- "transformers_version": "4.30.2",
23
- "vocab_size": 49408
24
- }
 
1
+ {
2
+ "architectures": [
3
+ "CLIPTextModelWithProjection"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 0,
7
+ "dropout": 0.0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_size": 1280,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5120,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 77,
16
+ "model_type": "clip_text_model",
17
+ "num_attention_heads": 20,
18
+ "num_hidden_layers": 32,
19
+ "pad_token_id": 1,
20
+ "projection_dim": 1280,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.34.0",
23
+ "vocab_size": 49408
24
+ }
text_encoder_2/model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d17bcfa80130be63ab58192e900671c1c427dcd7a8985e4778092b08c56fe27
3
+ size 1389382176
text_encoder_2/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:616d49756f37d3d250d9115f394bc8ec2b92f891ff3a744e5ece580bc82c3835
3
+ size 2778702264
tokenizer/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 49407,
3
+ "<|startoftext|>": 49406
4
+ }
tokenizer/merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer/special_tokens_map.json CHANGED
@@ -1,24 +1,6 @@
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
- }
 
1
+ {
2
+ "bos_token": "<|startoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer/tokenizer_config.json CHANGED
@@ -1,33 +1,32 @@
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
- "clean_up_tokenization_spaces": true,
12
- "do_lower_case": true,
13
- "eos_token": {
14
- "__type": "AddedToken",
15
- "content": "<|endoftext|>",
16
- "lstrip": false,
17
- "normalized": true,
18
- "rstrip": false,
19
- "single_word": false
20
- },
21
- "errors": "replace",
22
- "model_max_length": 77,
23
- "pad_token": "<|endoftext|>",
24
- "tokenizer_class": "CLIPTokenizer",
25
- "unk_token": {
26
- "__type": "AddedToken",
27
- "content": "<|endoftext|>",
28
- "lstrip": false,
29
- "normalized": true,
30
- "rstrip": false,
31
- "single_word": false
32
- }
33
- }
 
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": false
11
+ },
12
+ "49407": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ }
20
+ },
21
+ "additional_special_tokens": [],
22
+ "bos_token": "<|startoftext|>",
23
+ "clean_up_tokenization_spaces": true,
24
+ "do_lower_case": true,
25
+ "eos_token": "<|endoftext|>",
26
+ "errors": "replace",
27
+ "model_max_length": 77,
28
+ "pad_token": "<|endoftext|>",
29
+ "tokenizer_class": "CLIPTokenizer",
30
+ "tokenizer_file": "/home/user/.cache/huggingface/hub/models--openai--clip-vit-large-patch14/snapshots/32bd64288804d66eefd0ccbe215aa642df71cc41/tokenizer.json",
31
+ "unk_token": "<|endoftext|>"
32
+ }
 
tokenizer/vocab.json CHANGED
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 CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_2/special_tokens_map.json CHANGED
@@ -1,24 +1,6 @@
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
- }
 
1
+ {
2
+ "bos_token": "<|startoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "!",
5
+ "unk_token": "<|endoftext|>"
6
+ }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer_2/tokenizer_config.json CHANGED
@@ -1,33 +1,40 @@
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
- "clean_up_tokenization_spaces": true,
12
- "do_lower_case": true,
13
- "eos_token": {
14
- "__type": "AddedToken",
15
- "content": "<|endoftext|>",
16
- "lstrip": false,
17
- "normalized": true,
18
- "rstrip": false,
19
- "single_word": false
20
- },
21
- "errors": "replace",
22
- "model_max_length": 77,
23
- "pad_token": "!",
24
- "tokenizer_class": "CLIPTokenizer",
25
- "unk_token": {
26
- "__type": "AddedToken",
27
- "content": "<|endoftext|>",
28
- "lstrip": false,
29
- "normalized": true,
30
- "rstrip": false,
31
- "single_word": false
32
- }
33
- }
 
 
 
 
 
 
 
 
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": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ },
20
+ "49407": {
21
+ "content": "<|endoftext|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ }
28
+ },
29
+ "additional_special_tokens": [],
30
+ "bos_token": "<|startoftext|>",
31
+ "clean_up_tokenization_spaces": true,
32
+ "do_lower_case": true,
33
+ "eos_token": "<|endoftext|>",
34
+ "errors": "replace",
35
+ "model_max_length": 77,
36
+ "pad_token": "!",
37
+ "tokenizer_class": "CLIPTokenizer",
38
+ "tokenizer_file": "/home/user/.cache/huggingface/hub/models--laion--CLIP-ViT-bigG-14-laion2B-39B-b160k/snapshots/bc7788f151930d91b58474715fdce5524ad9a189/tokenizer.json",
39
+ "unk_token": "<|endoftext|>"
40
+ }
tokenizer_2/vocab.json CHANGED
The diff for this file is too large to render. See raw diff
 
unet/config.json CHANGED
@@ -1,72 +1,71 @@
1
- {
2
- "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.26.3",
4
- "act_fn": "silu",
5
- "addition_embed_type": "text_time",
6
- "addition_embed_type_num_heads": 64,
7
- "addition_time_embed_dim": 256,
8
- "attention_head_dim": [
9
- 5,
10
- 10,
11
- 20
12
- ],
13
- "attention_type": "default",
14
- "block_out_channels": [
15
- 320,
16
- 640,
17
- 1280
18
- ],
19
- "center_input_sample": false,
20
- "class_embed_type": null,
21
- "class_embeddings_concat": false,
22
- "conv_in_kernel": 3,
23
- "conv_out_kernel": 3,
24
- "cross_attention_dim": 2048,
25
- "cross_attention_norm": null,
26
- "down_block_types": [
27
- "DownBlock2D",
28
- "CrossAttnDownBlock2D",
29
- "CrossAttnDownBlock2D"
30
- ],
31
- "downsample_padding": 1,
32
- "dropout": 0.0,
33
- "dual_cross_attention": false,
34
- "encoder_hid_dim": null,
35
- "encoder_hid_dim_type": null,
36
- "flip_sin_to_cos": true,
37
- "freq_shift": 0,
38
- "in_channels": 4,
39
- "layers_per_block": 2,
40
- "mid_block_only_cross_attention": null,
41
- "mid_block_scale_factor": 1,
42
- "mid_block_type": "UNetMidBlock2DCrossAttn",
43
- "norm_eps": 1e-05,
44
- "norm_num_groups": 32,
45
- "num_attention_heads": null,
46
- "num_class_embeds": null,
47
- "only_cross_attention": false,
48
- "out_channels": 4,
49
- "projection_class_embeddings_input_dim": 2816,
50
- "resnet_out_scale_factor": 1.0,
51
- "resnet_skip_time_act": false,
52
- "resnet_time_scale_shift": "default",
53
- "reverse_transformer_layers_per_block": null,
54
- "sample_size": 128,
55
- "time_cond_proj_dim": null,
56
- "time_embedding_act_fn": null,
57
- "time_embedding_dim": null,
58
- "time_embedding_type": "positional",
59
- "timestep_post_act": null,
60
- "transformer_layers_per_block": [
61
- 1,
62
- 2,
63
- 10
64
- ],
65
- "up_block_types": [
66
- "CrossAttnUpBlock2D",
67
- "CrossAttnUpBlock2D",
68
- "UpBlock2D"
69
- ],
70
- "upcast_attention": false,
71
- "use_linear_projection": true
72
- }
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "act_fn": "silu",
5
+ "addition_embed_type": "text_time",
6
+ "addition_embed_type_num_heads": 64,
7
+ "addition_time_embed_dim": 256,
8
+ "attention_head_dim": [
9
+ 5,
10
+ 10,
11
+ 20
12
+ ],
13
+ "attention_type": "default",
14
+ "block_out_channels": [
15
+ 320,
16
+ 640,
17
+ 1280
18
+ ],
19
+ "center_input_sample": false,
20
+ "class_embed_type": null,
21
+ "class_embeddings_concat": false,
22
+ "conv_in_kernel": 3,
23
+ "conv_out_kernel": 3,
24
+ "cross_attention_dim": 2048,
25
+ "cross_attention_norm": null,
26
+ "down_block_types": [
27
+ "DownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "CrossAttnDownBlock2D"
30
+ ],
31
+ "downsample_padding": 1,
32
+ "dropout": 0.0,
33
+ "dual_cross_attention": false,
34
+ "encoder_hid_dim": null,
35
+ "encoder_hid_dim_type": null,
36
+ "flip_sin_to_cos": true,
37
+ "freq_shift": 0,
38
+ "in_channels": 4,
39
+ "layers_per_block": 2,
40
+ "mid_block_only_cross_attention": null,
41
+ "mid_block_scale_factor": 1,
42
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
43
+ "norm_eps": 1e-05,
44
+ "norm_num_groups": 32,
45
+ "num_attention_heads": null,
46
+ "num_class_embeds": null,
47
+ "only_cross_attention": false,
48
+ "out_channels": 4,
49
+ "projection_class_embeddings_input_dim": 2816,
50
+ "resnet_out_scale_factor": 1.0,
51
+ "resnet_skip_time_act": false,
52
+ "resnet_time_scale_shift": "default",
53
+ "sample_size": 128,
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": [
60
+ 1,
61
+ 2,
62
+ 10
63
+ ],
64
+ "up_block_types": [
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D",
67
+ "UpBlock2D"
68
+ ],
69
+ "upcast_attention": null,
70
+ "use_linear_projection": true
71
+ }
 
unet/diffusion_pytorch_model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a913326b73c0315e3ff1fd56d1f7672058e11648af8d161a3a0550b9a428ed62
3
+ size 5135149760
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5abb8d9b741aac0ae756cb67400a128b238a9cb9dd2212ca6ab3743c5db2455
3
+ size 10270077736
vae/config.json CHANGED
@@ -1,31 +1,31 @@
1
- {
2
- "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.26.3",
4
- "act_fn": "silu",
5
- "block_out_channels": [
6
- 128,
7
- 256,
8
- 512,
9
- 512
10
- ],
11
- "down_block_types": [
12
- "DownEncoderBlock2D",
13
- "DownEncoderBlock2D",
14
- "DownEncoderBlock2D",
15
- "DownEncoderBlock2D"
16
- ],
17
- "force_upcast": true,
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": 1024,
24
- "scaling_factor": 0.13025,
25
- "up_block_types": [
26
- "UpDecoderBlock2D",
27
- "UpDecoderBlock2D",
28
- "UpDecoderBlock2D",
29
- "UpDecoderBlock2D"
30
- ]
31
- }
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "act_fn": "silu",
5
+ "block_out_channels": [
6
+ 128,
7
+ 256,
8
+ 512,
9
+ 512
10
+ ],
11
+ "down_block_types": [
12
+ "DownEncoderBlock2D",
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D"
16
+ ],
17
+ "force_upcast": true,
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": 1024,
24
+ "scaling_factor": 0.13025,
25
+ "up_block_types": [
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D"
30
+ ]
31
+ }
vae/diffusion_pytorch_model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48
3
+ size 167335342
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98a14dc6fe8d71c83576f135a87c61a16561c9c080abba418d2cc976ee034f88
3
+ size 334643268