digiplay/Koji_v2.1_diffusers · Adding `diffusers` weights of this model (2025)

Files changed (20) hide show

  1. feature_extractor/preprocessor_config.json +28 -0
  2. model_index.json +33 -0
  3. safety_checker/config.json +28 -0
  4. safety_checker/model.fp16.safetensors +3 -0
  5. safety_checker/model.safetensors +3 -0
  6. scheduler/scheduler_config.json +19 -0
  7. text_encoder/config.json +24 -0
  8. text_encoder/model.fp16.safetensors +3 -0
  9. text_encoder/model.safetensors +3 -0
  10. tokenizer/added_tokens.json +4 -0
  11. tokenizer/merges.txt +0 -0
  12. tokenizer/special_tokens_map.json +6 -0
  13. tokenizer/tokenizer_config.json +32 -0
  14. tokenizer/vocab.json +0 -0
  15. unet/config.json +66 -0
  16. unet/diffusion_pytorch_model.fp16.safetensors +3 -0
  17. unet/diffusion_pytorch_model.safetensors +3 -0
  18. vae/config.json +31 -0
  19. vae/diffusion_pytorch_model.fp16.safetensors +3 -0
  20. vae/diffusion_pytorch_model.safetensors +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

+ }

model_index.json ADDED

@@ -0,0 +1,33 @@
1

+ {

2

+ "_class_name": "StableDiffusionPipeline",

3

+ "_diffusers_version": "0.22.0.dev0",

4

+ "feature_extractor": [

5

+ "transformers",

6

+ "CLIPFeatureExtractor"

7

+ ],

8

+ "requires_safety_checker": true,

9

+ "safety_checker": [

10

+ "stable_diffusion",

11

+ "StableDiffusionSafetyChecker"

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

+ }

safety_checker/config.json ADDED

@@ -0,0 +1,28 @@
1

+ {

2

+ "_name_or_path": "CompVis/stable-diffusion-safety-checker",

3

+ "architectures": [

4

+ "StableDiffusionSafetyChecker"

5

+ ],

6

+ "initializer_factor": 1.0,

7

+ "logit_scale_init_value": 2.6592,

8

+ "model_type": "clip",

9

+ "projection_dim": 768,

10

+ "text_config": {

11

+ "dropout": 0.0,

12

+ "hidden_size": 768,

13

+ "intermediate_size": 3072,

14

+ "model_type": "clip_text_model",

15

+ "num_attention_heads": 12

16

+ },

17

+ "torch_dtype": "float16",

18

+ "transformers_version": "4.34.0",

19

+ "vision_config": {

20

+ "dropout": 0.0,

21

+ "hidden_size": 1024,

22

+ "intermediate_size": 4096,

23

+ "model_type": "clip_vision_model",

24

+ "num_attention_heads": 16,

25

+ "num_hidden_layers": 24,

26

+ "patch_size": 14

27

+ }

28

+ }

safety_checker/model.fp16.safetensors ADDED

@@ -0,0 +1,3 @@
1

+ version https://git-lfs.github.com/spec/v1

2

+ oid sha256:57ecdfa243b170f9b4cb3eefaf0f64552ef78fc0bf0eb1c5b9675308447184f6

3

+ size 608016280

safety_checker/model.safetensors ADDED

@@ -0,0 +1,3 @@
1

+ version https://git-lfs.github.com/spec/v1

2

+ oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8

3

+ size 1215979664

scheduler/scheduler_config.json ADDED

@@ -0,0 +1,19 @@
1

+ {

2

+ "_class_name": "DDIMScheduler",

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

+ "clip_sample_range": 1.0,

9

+ "dynamic_thresholding_ratio": 0.995,

10

+ "num_train_timesteps": 1000,

11

+ "prediction_type": "epsilon",

12

+ "rescale_betas_zero_snr": false,

13

+ "sample_max_value": 1.0,

14

+ "set_alpha_to_one": false,

15

+ "steps_offset": 1,

16

+ "thresholding": false,

17

+ "timestep_spacing": "leading",

18

+ "trained_betas": null

19

+ }

text_encoder/config.json ADDED

@@ -0,0 +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": "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:df541f6b0bb74513aa7e01eb9a81d95f4e8079f5f77cd52dc1be98f1f7b0e3f2

3

+ size 246144152

text_encoder/model.safetensors ADDED

@@ -0,0 +1,3 @@
1

+ version https://git-lfs.github.com/spec/v1

2

+ oid sha256:f6d39cd6a8049f384d7d440b7c00ec5529dd80d28be1fe83be06009db118da14

3

+ size 492265168

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 +1,6 @@
1

+ {

2

+ "bos_token": "<|startoftext|>",

3

+ "eos_token": "<|endoftext|>",

4

+ "pad_token": "<|endoftext|>",

5

+ "unk_token": "<|endoftext|>"

6

+ }

tokenizer/tokenizer_config.json ADDED

@@ -0,0 +1,32 @@
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 ADDED

The diff for this file is too large to render. See raw diff

unet/config.json ADDED

@@ -0,0 +1,66 @@
1

+ {

2

+ "_class_name": "UNet2DConditionModel",

3

+ "_diffusers_version": "0.22.0.dev0",

4

+ "act_fn": "silu",

5

+ "addition_embed_type": null,

6

+ "addition_embed_type_num_heads": 64,

7

+ "addition_time_embed_dim": null,

8

+ "attention_head_dim": 8,

9

+ "attention_type": "default",

10

+ "block_out_channels": [

11

+ 320,

12

+ 640,

13

+ 1280,

14

+ 1280

15

+ ],

16

+ "center_input_sample": false,

17

+ "class_embed_type": null,

18

+ "class_embeddings_concat": false,

19

+ "conv_in_kernel": 3,

20

+ "conv_out_kernel": 3,

21

+ "cross_attention_dim": 768,

22

+ "cross_attention_norm": null,

23

+ "down_block_types": [

24

+ "CrossAttnDownBlock2D",

25

+ "CrossAttnDownBlock2D",

26

+ "CrossAttnDownBlock2D",

27

+ "DownBlock2D"

28

+ ],

29

+ "downsample_padding": 1,

30

+ "dropout": 0.0,

31

+ "dual_cross_attention": false,

32

+ "encoder_hid_dim": null,

33

+ "encoder_hid_dim_type": null,

34

+ "flip_sin_to_cos": true,

35

+ "freq_shift": 0,

36

+ "in_channels": 4,

37

+ "layers_per_block": 2,

38

+ "mid_block_only_cross_attention": null,

39

+ "mid_block_scale_factor": 1,

40

+ "mid_block_type": "UNetMidBlock2DCrossAttn",

41

+ "norm_eps": 1e-05,

42

+ "norm_num_groups": 32,

43

+ "num_attention_heads": null,

44

+ "num_class_embeds": null,

45

+ "only_cross_attention": false,

46

+ "out_channels": 4,

47

+ "projection_class_embeddings_input_dim": null,

48

+ "resnet_out_scale_factor": 1.0,

49

+ "resnet_skip_time_act": false,

50

+ "resnet_time_scale_shift": "default",

51

+ "sample_size": 96,

52

+ "time_cond_proj_dim": null,

53

+ "time_embedding_act_fn": null,

54

+ "time_embedding_dim": null,

55

+ "time_embedding_type": "positional",

56

+ "timestep_post_act": null,

57

+ "transformer_layers_per_block": 1,

58

+ "up_block_types": [

59

+ "UpBlock2D",

60

+ "CrossAttnUpBlock2D",

61

+ "CrossAttnUpBlock2D",

62

+ "CrossAttnUpBlock2D"

63

+ ],

64

+ "upcast_attention": null,

65

+ "use_linear_projection": false

66

+ }

unet/diffusion_pytorch_model.fp16.safetensors ADDED

@@ -0,0 +1,3 @@
1

+ version https://git-lfs.github.com/spec/v1

2

+ oid sha256:ec41139ac308be8ba691d1606813c7836611f70f87fbd1e76948e7ea191f2e08

3

+ size 1719125304

unet/diffusion_pytorch_model.safetensors ADDED

@@ -0,0 +1,3 @@
1

+ version https://git-lfs.github.com/spec/v1

2

+ oid sha256:565de429ddc20d191587e819b35bcb3912ceecc8b7aa00f9ff46c9d1cd2a5da6

3

+ size 3438167536

vae/config.json ADDED

@@ -0,0 +1,31 @@
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": 768,

24

+ "scaling_factor": 0.18215,

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 sha256:9bcf93488ec515e4c968e12c80676ac174fa3d501563aaddb9f09991e6fd04ee

3

+ size 167335342

vae/diffusion_pytorch_model.safetensors ADDED

@@ -0,0 +1,3 @@
1

+ version https://git-lfs.github.com/spec/v1

2

+ oid sha256:0d31958bd43e93fd1ef7e34a22cbb1275994aebcf6433a06fa3408201a66b494

3

+ size 334643268

digiplay/Koji_v2.1_diffusers · Adding `diffusers` weights of this model (2025)

References

Top Articles
Tanke Biosciences Corp Announces the Appointment of John P. Hopkins Executive Chairman of the Board of Directors
Terra Invicta, the space 4X from the creators of XCOM's Long War mod, just got a massive update that adds exofighters, improved diplomacy, and 'advanced weapons' for its alien menace
Social media before bedtime wreaks havoc on our sleep − a sleep researcher explains why screens alone aren’t the main culprit
Latest Posts
Guy Ritchie's MobLand breaks record as Paramount+'s biggest global series ever with 2.2 million viewers out of the gate
Flaming fury: Unpaid worker sets Pattaya resort ablaze in protest
Recommended Articles
Article information

Author: Ouida Strosin DO

Last Updated:

Views: 6026

Rating: 4.6 / 5 (56 voted)

Reviews: 87% of readers found this page helpful

Author information

Name: Ouida Strosin DO

Birthday: 1995-04-27

Address: Suite 927 930 Kilback Radial, Candidaville, TN 87795

Phone: +8561498978366

Job: Legacy Manufacturing Specialist

Hobby: Singing, Mountain biking, Water sports, Water sports, Taxidermy, Polo, Pet

Introduction: My name is Ouida Strosin DO, I am a precious, combative, spotless, modern, spotless, beautiful, precious person who loves writing and wants to share my knowledge and understanding with you.