Adding `diffusers` weights of this model

#3
model_index.json CHANGED
@@ -1,18 +1,22 @@
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
- "_diffusers_version": "0.22.0.dev0",
4
  "feature_extractor": [
5
  "transformers",
6
  "CLIPFeatureExtractor"
7
  ],
8
- "requires_safety_checker": null,
9
- "safety_checker": [
10
  null,
11
  null
12
  ],
 
 
 
 
 
13
  "scheduler": [
14
  "diffusers",
15
- "EulerDiscreteScheduler"
16
  ],
17
  "text_encoder": [
18
  "transformers",
 
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.26.0.dev0",
4
  "feature_extractor": [
5
  "transformers",
6
  "CLIPFeatureExtractor"
7
  ],
8
+ "image_encoder": [
 
9
  null,
10
  null
11
  ],
12
+ "requires_safety_checker": true,
13
+ "safety_checker": [
14
+ "stable_diffusion",
15
+ "StableDiffusionSafetyChecker"
16
+ ],
17
  "scheduler": [
18
  "diffusers",
19
+ "DPMSolverMultistepScheduler"
20
  ],
21
  "text_encoder": [
22
  "transformers",
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": "4.36.2",
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 CHANGED
@@ -1,19 +1,27 @@
1
  {
2
- "_class_name": "EulerDiscreteScheduler",
3
- "_diffusers_version": "0.18.0.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
- "interpolation_type": "linear",
 
 
 
11
  "num_train_timesteps": 1000,
12
  "prediction_type": "epsilon",
13
  "sample_max_value": 1.0,
14
  "set_alpha_to_one": false,
 
 
15
  "steps_offset": 1,
16
  "thresholding": false,
 
17
  "trained_betas": null,
18
- "use_karras_sigmas": false
 
 
19
  }
 
1
  {
2
+ "_class_name": "DPMSolverMultistepScheduler",
3
+ "_diffusers_version": "0.26.0.dev0",
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
+ "euler_at_final": false,
11
+ "final_sigmas_type": "zero",
12
+ "lambda_min_clipped": -Infinity,
13
+ "lower_order_final": true,
14
  "num_train_timesteps": 1000,
15
  "prediction_type": "epsilon",
16
  "sample_max_value": 1.0,
17
  "set_alpha_to_one": false,
18
+ "solver_order": 2,
19
+ "solver_type": "midpoint",
20
  "steps_offset": 1,
21
  "thresholding": false,
22
+ "timestep_spacing": "linspace",
23
  "trained_betas": null,
24
+ "use_karras_sigmas": false,
25
+ "use_lu_lambdas": false,
26
+ "variance_type": null
27
  }
text_encoder/config.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "_name_or_path": "openai/clip-vit-large-patch14",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
@@ -20,6 +19,6 @@
20
  "pad_token_id": 1,
21
  "projection_dim": 768,
22
  "torch_dtype": "float16",
23
- "transformers_version": "4.29.2",
24
  "vocab_size": 49408
25
  }
 
1
  {
 
2
  "architectures": [
3
  "CLIPTextModel"
4
  ],
 
19
  "pad_token_id": 1,
20
  "projection_dim": 768,
21
  "torch_dtype": "float16",
22
+ "transformers_version": "4.36.2",
23
  "vocab_size": 49408
24
  }
text_encoder/model.fp16.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30757f87b4731b6c0d04962f7f18326442d17f8373b0507ddcc8c1c29bbe2d50
3
- size 246144864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe045e4fd4432189fa1449a8b48da9825dee63e860879c0f06c591fba8a968f3
3
+ size 246144152
text_encoder/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f541ba9afab47c91cd1dbc239edbc2dc2853da109492ed13d5ff0b6cc945616d
3
- size 492265880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d3ce7beaf5f205439cd72a298d5d1af4d97321b39edfbef9b3c5a60556c3248
3
+ size 492265168
tokenizer/special_tokens_map.json CHANGED
@@ -9,15 +9,21 @@
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
  }
 
9
  "eos_token": {
10
  "content": "<|endoftext|>",
11
  "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
  "rstrip": false,
21
  "single_word": false
22
  },
 
23
  "unk_token": {
24
  "content": "<|endoftext|>",
25
  "lstrip": false,
26
+ "normalized": false,
27
  "rstrip": false,
28
  "single_word": false
29
  }
tokenizer/tokenizer_config.json CHANGED
@@ -1,33 +1,30 @@
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": 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
+ "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
  }
unet/config.json CHANGED
@@ -1,10 +1,12 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.18.0.dev0",
4
  "act_fn": "silu",
5
  "addition_embed_type": null,
6
  "addition_embed_type_num_heads": 64,
 
7
  "attention_head_dim": 8,
 
8
  "block_out_channels": [
9
  320,
10
  640,
@@ -25,6 +27,7 @@
25
  "DownBlock2D"
26
  ],
27
  "downsample_padding": 1,
 
28
  "dual_cross_attention": false,
29
  "encoder_hid_dim": null,
30
  "encoder_hid_dim_type": null,
@@ -37,6 +40,7 @@
37
  "mid_block_type": "UNetMidBlock2DCrossAttn",
38
  "norm_eps": 1e-05,
39
  "norm_num_groups": 32,
 
40
  "num_class_embeds": null,
41
  "only_cross_attention": false,
42
  "out_channels": 4,
@@ -44,12 +48,14 @@
44
  "resnet_out_scale_factor": 1.0,
45
  "resnet_skip_time_act": false,
46
  "resnet_time_scale_shift": "default",
 
47
  "sample_size": 96,
48
  "time_cond_proj_dim": null,
49
  "time_embedding_act_fn": null,
50
  "time_embedding_dim": null,
51
  "time_embedding_type": "positional",
52
  "timestep_post_act": null,
 
53
  "up_block_types": [
54
  "UpBlock2D",
55
  "CrossAttnUpBlock2D",
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.26.0.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,
 
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,
 
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,
 
48
  "resnet_out_scale_factor": 1.0,
49
  "resnet_skip_time_act": false,
50
  "resnet_time_scale_shift": "default",
51
+ "reverse_transformer_layers_per_block": null,
52
  "sample_size": 96,
53
  "time_cond_proj_dim": null,
54
  "time_embedding_act_fn": null,
55
  "time_embedding_dim": null,
56
  "time_embedding_type": "positional",
57
  "timestep_post_act": null,
58
+ "transformer_layers_per_block": 1,
59
  "up_block_types": [
60
  "UpBlock2D",
61
  "CrossAttnUpBlock2D",
vae/config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.18.0.dev0",
4
  "act_fn": "silu",
5
  "block_out_channels": [
6
  128,
@@ -14,6 +14,7 @@
14
  "DownEncoderBlock2D",
15
  "DownEncoderBlock2D"
16
  ],
 
17
  "in_channels": 3,
18
  "latent_channels": 4,
19
  "layers_per_block": 2,
 
1
  {
2
  "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.26.0.dev0",
4
  "act_fn": "silu",
5
  "block_out_channels": [
6
  128,
 
14
  "DownEncoderBlock2D",
15
  "DownEncoderBlock2D"
16
  ],
17
+ "force_upcast": true,
18
  "in_channels": 3,
19
  "latent_channels": 4,
20
  "layers_per_block": 2,