Adding `diffusers` weights of this model (#4)

- Adding `diffusers` weights of this model (05f840b3c78bb09e6ce18bb6d41328a46e12a67d)

model_index.json

@@ -5,14 +5,14 @@
     "transformers",
     "CLIPFeatureExtractor"
   ],
-  "requires_safety_checker": null,
+  "requires_safety_checker": true,
   "safety_checker": [
-    null,
-    null
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
   ],
   "scheduler": [
     "diffusers",
-    "EulerAncestralDiscreteScheduler"
+    "EulerDiscreteScheduler"
   ],
   "text_encoder": [
     "transformers",

safety_checker/config.json

@@ -0,0 +1,168 @@
+{
+  "_commit_hash": "cb41f3a270d63d454d385fc2e4f571c487c253c5",
+  "_name_or_path": "CompVis/stable-diffusion-safety-checker",
+  "architectures": [
+    "StableDiffusionSafetyChecker"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 77,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.30.2",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49408
+  },
+  "torch_dtype": "float16",
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.30.2",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}

safety_checker/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08902f19b1cfebd7c989f152fc0507bef6898c706a91d666509383122324b511
+size 608018440

safety_checker/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11cfe53105625af8c00faac32a430626641cce686454f3c39d837f14397d858b
+size 1215981832

safety_checker/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
+size 1216064769

safety_checker/pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22ba87205445ad5def13e54919b038dcfb7321ec1c3f4b12487d4fba6036125f
+size 608103564

scheduler/scheduler_config.json

@@ -1,14 +1,21 @@
 {
-  "_class_name": "EulerAncestralDiscreteScheduler",
-  "_diffusers_version": "0.14.0",
+  "_class_name": "EulerDiscreteScheduler",
+  "_diffusers_version": "0.18.0.dev0",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
   "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
+  "interpolation_type": "linear",
   "num_train_timesteps": 1000,
   "prediction_type": "epsilon",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
   "set_alpha_to_one": false,
-  "skip_prk_steps": true,
   "steps_offset": 1,
-  "trained_betas": null
+  "thresholding": false,
+  "timestep_spacing": "leading",
+  "trained_betas": null,
+  "use_karras_sigmas": false
 }

text_encoder/config.json

@@ -16,7 +16,7 @@
   "max_position_embeddings": 77,
   "model_type": "clip_text_model",
   "num_attention_heads": 12,
-  "num_hidden_layers": 11,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "float16",

text_encoder/model.fp16.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2cbbea40ccc9f01afca4e69114df6df9a778c9a685eeb50b0c7522d3176355f
+oid sha256:37e6e0c661e3b97aa308e9514be395d271f07fee26561947d80dab62771480d2
 size 246144864

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50b57023d5d02b54b2ac54a66ba3810a84adcbdc9b63261bba47b0f9fd6c6bea
+oid sha256:598e3915422cb1f2fc4dadffd40b6a0a5b84544bac5f718aa40a12db2891f6bc
 size 492265880

text_encoder/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7d4df0c48e16e46222f9455f4c295d796701d1da9c59a287dcc0586bb776d4b
+oid sha256:169559eefdaeca53c3d515dd794035ce2bd0d98d5602cf36a5411039adb65b76
 size 492307041

text_encoder/pytorch_model.fp16.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c105d231db601e511e7621fc8a4158b5970791ee145b6245c16a046c95719355
+oid sha256:6d32e2d1b866366f45576ce205b3ff4a32efb72efe57b7e57d8a5535e92f2c74
 size 246187076

tokenizer/tokenizer_config.json

@@ -8,6 +8,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "clean_up_tokenization_spaces": true,
   "do_lower_case": true,
   "eos_token": {
     "__type": "AddedToken",
@@ -19,9 +20,7 @@
   },
   "errors": "replace",
   "model_max_length": 77,
-  "name_or_path": "openai/clip-vit-large-patch14",
   "pad_token": "<|endoftext|>",
-  "special_tokens_map_file": "./special_tokens_map.json",
   "tokenizer_class": "CLIPTokenizer",
   "unk_token": {
     "__type": "AddedToken",

unet/config.json

@@ -1,7 +1,9 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.14.0",
+  "_diffusers_version": "0.18.0.dev0",
   "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
   "attention_head_dim": 8,
   "block_out_channels": [
     320,
@@ -11,9 +13,11 @@
   ],
   "center_input_sample": false,
   "class_embed_type": null,
+  "class_embeddings_concat": false,
   "conv_in_kernel": 3,
   "conv_out_kernel": 3,
   "cross_attention_dim": 768,
+  "cross_attention_norm": null,
   "down_block_types": [
     "CrossAttnDownBlock2D",
     "CrossAttnDownBlock2D",
@@ -22,21 +26,29 @@
   ],
   "downsample_padding": 1,
   "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
   "flip_sin_to_cos": true,
   "freq_shift": 0,
   "in_channels": 4,
   "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
   "mid_block_scale_factor": 1,
   "mid_block_type": "UNetMidBlock2DCrossAttn",
   "norm_eps": 1e-05,
   "norm_num_groups": 32,
+  "num_attention_heads": null,
   "num_class_embeds": null,
   "only_cross_attention": false,
   "out_channels": 4,
   "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
   "resnet_time_scale_shift": "default",
   "sample_size": 64,
   "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
   "time_embedding_type": "positional",
   "timestep_post_act": null,
   "up_block_types": [
@@ -45,6 +57,6 @@
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
-  "upcast_attention": false,
+  "upcast_attention": null,
   "use_linear_projection": false
 }

unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57816bec8909cc7009dd50e26ebede2f1515147e80125477c93b81340f19fa5c
+oid sha256:caacca1f8b21aa9cdb99ae0ce8d6ff23d2fea302eacbf594f2493a75ee710d5b
 size 3438366373

unet/diffusion_pytorch_model.fp16.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1d3768373ad0c46c902acb41f5558c47e87d1c7b00140e407058229ae5b6f5f
+oid sha256:6822bee7cb03a7ccd0803222c52c903b7947722c87e8668c7d02e253091f144c
 size 1719327893

unet/diffusion_pytorch_model.fp16.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bb7b712815a1a6f227cb36f5e912a7e951270343c2b2a0734fa832136f29873
+oid sha256:c52f29603778a4e9654aa9629a4fa7affbc92c17e3306c0c797b0417064b0ebe
 size 1719125304

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a78af4da33e537d634d0a89becdb412dead657682aed8c7062fdeff2c2dafdf0
+oid sha256:3178a408e1f29850b7e291ef8f38d66b81a89cd08da9aa598d56c8c5c6f82dbe
 size 3438167536

vae/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48a0dfac27293c44d55a7f09eb1468c85e7cb0fc7b240548844c332ebbec0190
+oid sha256:31fef5fa5b3814b08002682045f776fc951ba2dacec7af6807018189516b121f
 size 334712113

vae/diffusion_pytorch_model.fp16.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd778c153d31691097d4123897fb7426fe8d938252beec13e6bd66bd0d8c5008
+oid sha256:d207e4928394a2002bcb7fff829e93bbd2a44bc323e597fdb690d3fc2d064de2
 size 167405651

vae/diffusion_pytorch_model.fp16.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6351d1fdaeae57bc2577834f9f212577349339a3c87a98987202927edd53cb73
+oid sha256:9d8fb415ab4f9782232e7bb82e618e2c0cef0be3593c77a35f5733d8fdd3530f
 size 167335342

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80829748b40310f1d82ecefc6dcac41a8680aa728fcb9c88b158f442cded1fed
+oid sha256:6e91305cd81f7d1387694a231b63de771190b3f2c25591eb71a8c2525cb08397
 size 334643268