Adding `diffusers` weights of this model (#3)

- Adding `diffusers` weights of this model (b682c45db83e659b072cea34b301f9c05cccc12d)

feature_extractor/preprocessor_config.json

@@ -8,7 +8,6 @@
   "do_normalize": true,
   "do_rescale": true,
   "do_resize": true,
-  "feature_extractor_type": "CLIPFeatureExtractor",
   "image_mean": [
     0.48145466,
     0.4578275,

model_index.json

@@ -5,11 +5,19 @@
     "transformers",
     "CLIPFeatureExtractor"
   ],
-  "requires_safety_checker": null,
-  "scheduler": [
+  "image_encoder": [
     null,
     null
   ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
+  ],
+  "scheduler": [
+    "diffusers",
+    "EulerDiscreteScheduler"
+  ],
   "text_encoder": [
     "transformers",
     "CLIPTextModel"

safety_checker/config.json

@@ -1,5 +1,4 @@
 {
-  "_commit_hash": "cb41f3a270d63d454d385fc2e4f571c487c253c5",
   "_name_or_path": "CompVis/stable-diffusion-safety-checker",
   "architectures": [
     "StableDiffusionSafetyChecker"
@@ -9,160 +8,21 @@
   "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": 49406,
-    "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": 49407,
-    "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": "4.31.0",
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "vocab_size": 49408
+    "num_attention_heads": 12
   },
   "torch_dtype": "float16",
-  "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,
-    "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": "4.31.0",
-    "typical_p": 1.0,
-    "use_bfloat16": false
+    "patch_size": 14
   }
 }

scheduler/scheduler_config.json

@@ -1,24 +1,20 @@
 {
-  "_class_name": "DPMSolverMultistepScheduler",
-  "_diffusers_version": "0.19.0.dev0",
-  "algorithm_type": "dpmsolver++",
+  "_class_name": "EulerDiscreteScheduler",
+  "_diffusers_version": "0.26.0.dev0",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
   "clip_sample": false,
-  "dynamic_thresholding_ratio": 0.995,
-  "lambda_min_clipped": -Infinity,
-  "lower_order_final": true,
+  "interpolation_type": "linear",
   "num_train_timesteps": 1000,
   "prediction_type": "epsilon",
-  "sample_max_value": 1.0,
+  "rescale_betas_zero_snr": false,
   "set_alpha_to_one": false,
-  "solver_order": 2,
-  "solver_type": "midpoint",
+  "sigma_max": null,
+  "sigma_min": null,
   "steps_offset": 1,
-  "thresholding": false,
   "timestep_spacing": "linspace",
+  "timestep_type": "discrete",
   "trained_betas": null,
-  "use_karras_sigmas": false,
-  "variance_type": null
+  "use_karras_sigmas": false
 }

text_encoder/config.json

@@ -19,6 +19,6 @@
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "float16",
-  "transformers_version": "4.31.0",
+  "transformers_version": "4.37.2",
   "vocab_size": 49408
 }

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

@@ -1,33 +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,
   "pad_token": "<|endoftext|>",
   "tokenizer_class": "CLIPTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "<|endoftext|>"
 }

unet/config.json

@@ -1,11 +1,12 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.19.0.dev0",
+  "_diffusers_version": "0.26.0.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,
@@ -26,6 +27,7 @@
     "DownBlock2D"
   ],
   "downsample_padding": 1,
+  "dropout": 0.0,
   "dual_cross_attention": false,
   "encoder_hid_dim": null,
   "encoder_hid_dim_type": null,
@@ -46,6 +48,7 @@
   "resnet_out_scale_factor": 1.0,
   "resnet_skip_time_act": false,
   "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
   "sample_size": 96,
   "time_cond_proj_dim": null,
   "time_embedding_act_fn": null,

vae/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.19.0.dev0",
+  "_diffusers_version": "0.26.0.dev0",
   "act_fn": "silu",
   "block_out_channels": [
     128,