Upload 15 files

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": "CLIPImageProcessor",
   "image_std": [
     0.26862954,
     0.26130258,
     0.27577711
   ],
   "resample": 3,
-  "size": 224
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
 }

model_index.json

@@ -1,15 +1,20 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.7.0.dev0",
+  "_diffusers_version": "0.31.0",
+  "_name_or_path": "tiny-stable-diffusion-with-safety-checker",
   "feature_extractor": [
     "transformers",
     "CLIPImageProcessor"
   ],
+  "image_encoder": [
+    null,
+    null
+  ],
   "requires_safety_checker": true,
   "safety_checker": [
-      "stable_diffusion",
-      "StableDiffusionSafetyChecker"
-    ],
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
+  ],
   "scheduler": [
     "diffusers",
     "PNDMScheduler"

safety_checker/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "CompVis/stable-diffusion-safety-checker",
+  "_name_or_path": "/home/ea/work/my_optimum_intel/optimum-intel/tiny-stable-diffusion-with-safety-checker/safety_checker",
   "architectures": [
     "StableDiffusionSafetyChecker"
   ],

scheduler/scheduler_config.json

@@ -1,13 +1,15 @@
 {
   "_class_name": "PNDMScheduler",
-  "_diffusers_version": "0.7.0.dev0",
+  "_diffusers_version": "0.31.0",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
+  "clip_sample": false,
   "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
   "set_alpha_to_one": false,
   "skip_prk_steps": true,
   "steps_offset": 1,
-  "trained_betas": null,
-  "clip_sample": false
+  "timestep_spacing": "leading",
+  "trained_betas": null
 }

text_encoder/config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "/home/ea/work/my_optimum_intel/optimum-intel/tiny-stable-diffusion-with-safety-checker/text_encoder",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -17,7 +18,8 @@
   "num_attention_heads": 4,
   "num_hidden_layers": 5,
   "pad_token_id": 1,
+  "projection_dim": 512,
   "torch_dtype": "float32",
-  "transformers_version": "4.22.2",
+  "transformers_version": "4.46.2",
   "vocab_size": 1000
 }

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:103860291b96610a23d9dda96f6a3c4e6c6dd67e5984a0d5e7c8e62769ac6412
+size 283212

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": {
+    "0": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
   },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
   "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": "hf-internal-testing/tiny-random-clip",
   "pad_token": "<|endoftext|>",
-  "special_tokens_map_file": "/home/lysandre/.cache/huggingface/transformers/18a566598f286c9139f88160c99f84eec492a26bd22738fa9cb44d5b7e0a5c76.cce1206abbad28826f000510f22f354e53e66a97f7c23745a7dfe27609cc07f5",
   "tokenizer_class": "CLIPTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "<|endoftext|>"
 }

unet/config.json

@@ -1,30 +1,62 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.7.0.dev0",
+  "_diffusers_version": "0.31.0",
+  "_name_or_path": "/home/ea/work/my_optimum_intel/optimum-intel/tiny-stable-diffusion-with-safety-checker/unet",
   "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": [
     32,
     64
   ],
   "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
   "cross_attention_dim": 32,
+  "cross_attention_norm": null,
   "down_block_types": [
     "DownBlock2D",
     "CrossAttnDownBlock2D"
   ],
   "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,
-  "sample_size": 32,
+  "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": [
     "CrossAttnUpBlock2D",
     "UpBlock2D"
-  ]
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
 }

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c69e435ef37a4e0fe3471d2c9488924bdf534cb51c08e9450420784d53336d73
+size 5742160

vae/config.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.7.0.dev0",
+  "_diffusers_version": "0.31.0",
+  "_name_or_path": "/home/ea/work/my_optimum_intel/optimum-intel/tiny-stable-diffusion-with-safety-checker/vae",
   "act_fn": "silu",
   "block_out_channels": [
     32,
@@ -10,14 +11,22 @@
     "DownEncoderBlock2D",
     "DownEncoderBlock2D"
   ],
+  "force_upcast": true,
   "in_channels": 3,
   "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
   "layers_per_block": 1,
+  "mid_block_add_attention": true,
   "norm_num_groups": 32,
   "out_channels": 3,
   "sample_size": 128,
+  "scaling_factor": 0.18215,
+  "shift_factor": null,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D"
-  ]
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
 }

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7999b516094ac4239121d9f62a37e6be99620e7016220011bb99cf8b1a391aad
+size 2646532