Upload 16 files (#4)

- Upload 16 files (dadf947a53fc0983b7759cb1f38ea9a67084b11f)

feature_extractor/preprocessor_config.json

@@ -1,12 +1,8 @@
 {
-  "crop_size": {
-    "height": 224,
-    "width": 224
-  },
+  "crop_size": 224,
   "do_center_crop": true,
   "do_convert_rgb": true,
   "do_normalize": true,
-  "do_rescale": true,
   "do_resize": true,
   "feature_extractor_type": "CLIPFeatureExtractor",
   "image_mean": [
@@ -14,15 +10,11 @@
     0.4578275,
     0.40821073
   ],
-  "image_processor_type": "CLIPFeatureExtractor",
   "image_std": [
     0.26862954,
     0.26130258,
     0.27577711
   ],
   "resample": 3,
-  "rescale_factor": 0.00392156862745098,
-  "size": {
-    "shortest_edge": 224
-  }
+  "size": 224
 }

safety_checker/config.json

@@ -1,8 +1,7 @@
 {
-  "_commit_hash": "cb41f3a270d63d454d385fc2e4f571c487c253c5",
-  "_name_or_path": "CompVis/stable-diffusion-safety-checker",
+  "_name_or_path": "clip-vit-large-patch14/",
   "architectures": [
-    "StableDiffusionSafetyChecker"
+    "SafetyChecker"
   ],
   "initializer_factor": 1.0,
   "logit_scale_init_value": 2.6592,
@@ -14,7 +13,6 @@
     "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,
@@ -62,17 +60,14 @@
     "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,
@@ -80,7 +75,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.26.0.dev0",
+    "transformers_version": "4.21.0.dev0",
     "typical_p": 1.0,
     "use_bfloat16": false,
     "vocab_size": 49408
@@ -99,7 +94,6 @@
     "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,
@@ -139,7 +133,6 @@
     "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,
@@ -149,17 +142,14 @@
     "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,
@@ -167,7 +157,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.26.0.dev0",
+    "transformers_version": "4.21.0.dev0",
     "typical_p": 1.0,
     "use_bfloat16": false
   },

safety_checker/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
-size 1216064769
+oid sha256:64b8393f1afd5a0c1ed2aa5f341fa7c08286839a48f3743162a76a2835c808bd
+size 1216067303

scheduler/scheduler_config.json

@@ -1,6 +1,6 @@
 {
-  "_class_name": "PNDMScheduler",
-  "_diffusers_version": "0.12.0.dev0",
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.10.2",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
@@ -11,4 +11,4 @@
   "skip_prk_steps": true,
   "steps_offset": 1,
   "trained_betas": null
-}
+}

text_encoder/config.json

@@ -20,6 +20,6 @@
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "float32",
-  "transformers_version": "4.26.0.dev0",
+  "transformers_version": "4.25.1",
   "vocab_size": 49408
 }

text_encoder/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a375c8d147585ec7223d47e64b1cfedb63069f42c949eb85237413e5bb4f8b6
+oid sha256:8d1524362379cb659b9f0bf9b8e4970cd2aea08a6657dbfd51606c64ebeec8ed
 size 492307041

tokenizer/tokenizer_config.json

@@ -23,20 +23,6 @@
   "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
-    },
-  "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|>",

unet/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.12.0.dev0",
+  "_diffusers_version": "0.10.2",
   "act_fn": "silu",
   "attention_head_dim": 8,
   "block_out_channels": [
@@ -10,7 +10,6 @@
     1280
   ],
   "center_input_sample": false,
-  "class_embed_type": null,
   "cross_attention_dim": 768,
   "down_block_types": [
     "CrossAttnDownBlock2D",
@@ -25,14 +24,12 @@
   "in_channels": 4,
   "layers_per_block": 2,
   "mid_block_scale_factor": 1,
-  "mid_block_type": "UNetMidBlock2DCrossAttn",
   "norm_eps": 1e-05,
   "norm_num_groups": 32,
   "num_class_embeds": null,
   "only_cross_attention": false,
   "out_channels": 4,
-  "resnet_time_scale_shift": "default",
-  "sample_size": 64,
+  "sample_size": 32,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",

unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a2c73c5c7c2a31252f3a450689433a8f8acd24cc533d68a8d043f99d0a0312b
+oid sha256:c727c1864179e43a3338a99e28e08f9c7b12cd46e56e60afb429e17c57644c14
 size 3438366373

vae/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.12.0.dev0",
+  "_diffusers_version": "0.10.2",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -19,7 +19,7 @@
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 512,
+  "sample_size": 256,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",

vae/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39c39d36eb762d178c878bcdd743f75ae609c6e13848f0a69c574d32d7ed3ab3
+oid sha256:876a906810a8b2470c3092f307742f6ad8b9dbf759fb7c0ff020d0c610c996da
 size 334711857