Adding `diffusers` weights of this model

This PR adds fp32 and fp16 weights in PyTorch and safetensors format to runwayml/stable-diffusion-v1-5

feature_extractor/preprocessor_config.json

@@ -1,20 +1,27 @@
 {
-  "crop_size": 224,
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
   "do_center_crop": true,
   "do_convert_rgb": true,
   "do_normalize": true,
+  "do_rescale": true,
   "do_resize": true,
-  "feature_extractor_type": "CLIPFeatureExtractor",
   "image_mean": [
     0.48145466,
     0.4578275,
     0.40821073
   ],
+  "image_processor_type": "CLIPFeatureExtractor",
   "image_std": [
     0.26862954,
     0.26130258,
     0.27577711
   ],
   "resample": 3,
-  "size": 224
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
 }

model_index.json

@@ -1,17 +1,22 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.6.0",
+  "_diffusers_version": "0.27.0.dev0",
   "feature_extractor": [
     "transformers",
-    "CLIPImageProcessor"
+    "CLIPFeatureExtractor"
   ],
+  "image_encoder": [
+    null,
+    null
+  ],
+  "requires_safety_checker": true,
   "safety_checker": [
     "stable_diffusion",
     "StableDiffusionSafetyChecker"
   ],
   "scheduler": [
     "diffusers",
-    "PNDMScheduler"
+    "DPMSolverMultistepScheduler"
   ],
   "text_encoder": [
     "transformers",

safety_checker/config.json

@@ -1,5 +1,4 @@
 {
-  "_commit_hash": "4bb648a606ef040e7685bde262611766a5fdd67b",
   "_name_or_path": "CompVis/stable-diffusion-safety-checker",
   "architectures": [
     "StableDiffusionSafetyChecker"
@@ -9,165 +8,19 @@
   "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,
-    "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,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": 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": "4.22.0.dev0",
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "vocab_size": 49408
-  },
-  "text_config_dict": {
-    "hidden_size": 768,
-    "intermediate_size": 3072,
-    "num_attention_heads": 12,
-    "num_hidden_layers": 12
+    "num_attention_heads": 12
   },
   "torch_dtype": "float32",
-  "transformers_version": null,
+  "transformers_version": "4.37.2",
   "vision_config": {
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": null,
-    "attention_dropout": 0.0,
-    "bad_words_ids": 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,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": 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": "4.22.0.dev0",
-    "typical_p": 1.0,
-    "use_bfloat16": false
-  },
-  "vision_config_dict": {
-    "hidden_size": 1024,
-    "intermediate_size": 4096,
     "num_attention_heads": 16,
     "num_hidden_layers": 24,
     "patch_size": 14

safety_checker/model.fp16.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08902f19b1cfebd7c989f152fc0507bef6898c706a91d666509383122324b511
-size 608018440
+oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
+size 1215979664

safety_checker/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d6a233ff6fd5ccb9f76fd99618d73369c52dd3d8222376384d0e601911089e8
-size 1215981830
+oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
+size 1215979664

scheduler/scheduler_config.json

@@ -1,13 +1,27 @@
 {
-  "_class_name": "PNDMScheduler",
-  "_diffusers_version": "0.6.0",
+  "_class_name": "DPMSolverMultistepScheduler",
+  "_diffusers_version": "0.27.0.dev0",
+  "algorithm_type": "dpmsolver++",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
+  "clip_sample": false,
+  "dynamic_thresholding_ratio": 0.995,
+  "euler_at_final": false,
+  "final_sigmas_type": "zero",
+  "lambda_min_clipped": -Infinity,
+  "lower_order_final": true,
   "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "sample_max_value": 1.0,
   "set_alpha_to_one": false,
-  "skip_prk_steps": true,
+  "solver_order": 2,
+  "solver_type": "midpoint",
   "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "linspace",
   "trained_betas": null,
-  "clip_sample": false
+  "use_karras_sigmas": false,
+  "use_lu_lambdas": false,
+  "variance_type": null
 }

text_encoder/config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "openai/clip-vit-large-patch14",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -20,6 +19,6 @@
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "float32",
-  "transformers_version": "4.22.0.dev0",
+  "transformers_version": "4.37.2",
   "vocab_size": 49408
 }

text_encoder/model.fp16.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77795e2023adcf39bc29a884661950380bd093cf0750a966d473d1718dc9ef4e
-size 246144864
+oid sha256:778d02eb9e707c3fbaae0b67b79ea0d1399b52e624fb634f2f19375ae7c047c3
+size 492265168

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d008943c017f0092921106440254dbbe00b6a285f7883ec8ba160c3faad88334
-size 492265874
+oid sha256:778d02eb9e707c3fbaae0b67b79ea0d1399b52e624fb634f2f19375ae7c047c3
+size 492265168

tokenizer/special_tokens_map.json

@@ -9,15 +9,21 @@
   "eos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer/tokenizer_config.json

@@ -1,34 +1,30 @@
 {
   "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<|startoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
   },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
   "do_lower_case": true,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "eos_token": "<|endoftext|>",
   "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",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "<|endoftext|>"
 }

unet/config.json

@@ -1,8 +1,12 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.6.0",
+  "_diffusers_version": "0.27.0.dev0",
   "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
   "attention_head_dim": 8,
+  "attention_type": "default",
   "block_out_channels": [
     320,
     640,
@@ -10,7 +14,12 @@
     1280
   ],
   "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",
@@ -18,19 +27,41 @@
     "DownBlock2D"
   ],
   "downsample_padding": 1,
+  "dropout": 0.0,
+  "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",
+  "reverse_transformer_layers_per_block": null,
   "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,
+  "transformer_layers_per_block": 1,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
-  ]
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": false
 }

unet/diffusion_pytorch_model.fp16.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c83908253f9a64d08c25fc90874c9c8aef9a329ce1ca5fb909d73b0c83d1ea21
-size 1719125304
+oid sha256:d27cd69d4a0aa32105087a619f32a51bc087e133be93fe23da92f3c0bcc07d79
+size 3438167536

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19da7aaa4b880e59d56843f1fcb4dd9b599c28a1d9d9af7c1143057c8ffae9f1
-size 3438167540
+oid sha256:d27cd69d4a0aa32105087a619f32a51bc087e133be93fe23da92f3c0bcc07d79
+size 3438167536

vae/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.6.0",
+  "_diffusers_version": "0.27.0.dev0",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -14,12 +14,14 @@
     "DownEncoderBlock2D",
     "DownEncoderBlock2D"
   ],
+  "force_upcast": true,
   "in_channels": 3,
   "latent_channels": 4,
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
   "sample_size": 512,
+  "scaling_factor": 0.18215,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",

vae/diffusion_pytorch_model.fp16.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c
-size 167335342
+oid sha256:b4d2b5932bb4151e54e694fd31ccf51fca908223c9485bd56cd0e1d83ad94c49
+size 334643268

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2b5134f4dbc140d9c11f11cba3233099e00af40f262f136c691fb7d38d2194c
-size 334643276
+oid sha256:b4d2b5932bb4151e54e694fd31ccf51fca908223c9485bd56cd0e1d83ad94c49
+size 334643268