Adding `diffusers` weights of this model

This PR adds fp32 and fp16 weights in PyTorch and safetensors format to rowenac/vintagechinesecomics

feature_extractor/preprocessor_config.json

@@ -1,8 +1,12 @@
 {
-  "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": [
@@ -10,11 +14,15 @@
     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

@@ -1,33 +1,33 @@
 {
-    "_class_name": "StableDiffusionPipeline",
-    "_diffusers_version": "0.10.2",
-    "feature_extractor": [
-        null,
-        null
-    ],
-    "requires_safety_checker": null,
-    "safety_checker": [
-        null,
-        null
-    ],
-    "scheduler": [
-        "diffusers",
-        "DEISMultistepScheduler"
-    ],
-    "text_encoder": [
-        "transformers",
-        "CLIPTextModel"
-    ],
-    "tokenizer": [
-        "transformers",
-        "CLIPTokenizer"
-    ],
-    "unet": [
-        "diffusers",
-        "UNet2DConditionModel"
-    ],
-    "vae": [
-        "diffusers",
-        "AutoencoderKL"
-    ]
-}
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.18.0.dev0",
+  "feature_extractor": [
+    "transformers",
+    "CLIPFeatureExtractor"
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
+  ],
+  "scheduler": [
+    "diffusers",
+    "DPMSolverMultistepScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

safety_checker/config.json

@@ -1,5 +1,5 @@
 {
-  "_commit_hash": "4bb648a606ef040e7685bde262611766a5fdd67b",
+  "_commit_hash": "cb41f3a270d63d454d385fc2e4f571c487c253c5",
   "_name_or_path": "CompVis/stable-diffusion-safety-checker",
   "architectures": [
     "StableDiffusionSafetyChecker"
@@ -14,6 +14,7 @@
     "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,
@@ -61,12 +62,14 @@
     "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,
@@ -77,18 +80,12 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.22.0.dev0",
+    "transformers_version": "4.30.2",
     "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
-  },
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": null,
   "vision_config": {
     "_name_or_path": "",
@@ -96,6 +93,7 @@
     "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,
@@ -145,12 +143,14 @@
     "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,
@@ -161,15 +161,8 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.22.0.dev0",
+    "transformers_version": "4.30.2",
     "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.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d6a233ff6fd5ccb9f76fd99618d73369c52dd3d8222376384d0e601911089e8
-size 1215981830
+oid sha256:11cfe53105625af8c00faac32a430626641cce686454f3c39d837f14397d858b
+size 1215981832

safety_checker/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:193490b58ef62739077262e833bf091c66c29488058681ac25cf7df3d8190974
-size 1216061799
+oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
+size 1216064769

scheduler/scheduler_config.json

@@ -1,13 +1,26 @@
 {
-  "_class_name": "PNDMScheduler",
-  "_diffusers_version": "0.6.0",
+  "_class_name": "DPMSolverMultistepScheduler",
+  "_diffusers_version": "0.18.0.dev0",
+  "algorithm_type": "dpmsolver++",
   "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,
+  "lambda_min_clipped": -Infinity,
+  "lower_order_final": true,
   "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,
+  "solver_order": 2,
+  "solver_type": "midpoint",
   "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "leading",
   "trained_betas": null,
-  "clip_sample": false
+  "use_karras_sigmas": false,
+  "variance_type": null
 }

text_encoder/config.json

@@ -19,7 +19,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "projection_dim": 768,
-  "torch_dtype": "float32",
-  "transformers_version": "4.22.0.dev0",
+  "torch_dtype": "float16",
+  "transformers_version": "4.30.2",
   "vocab_size": 49408
 }

text_encoder/model.fp16.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77795e2023adcf39bc29a884661950380bd093cf0750a966d473d1718dc9ef4e
+oid sha256:c0015c415929a8b8b49dd5cf90fdbf43ac7061e7d8f1e9be5134e1bd0e2d2f11
 size 246144864

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d008943c017f0092921106440254dbbe00b6a285f7883ec8ba160c3faad88334
-size 492265874
+oid sha256:0ec9ff53f7e708239f3653e7ccb4f8921e25b21add7bf4f04692f211a9f3b96d
+size 492265880

text_encoder/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:770a47a9ffdcfda0b05506a7888ed714d06131d60267e6cf52765d61cf59fd67
-size 492305335
+oid sha256:858b979347883f1b6eab988d9644bbea0fc91af5eb42ab81b64ad0c38ba589a4
+size 492307041

text_encoder/pytorch_model.fp16.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05eee911f195625deeab86f0b22b115d7d8bc3adbfc1404f03557f7e4e6a8fd7
+oid sha256:6015720b88647568ebc627db9e5dd5e8a718b6b343f483e86501afd2a946f80f
 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": "0.6.0",
+  "_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,
@@ -10,7 +12,12 @@
     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 +25,38 @@
     "DownBlock2D"
   ],
   "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": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
-  ]
+  ],
+  "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:c7da0e21ba7ea50637bee26e81c220844defdf01aafca02b2c42ecdadb813de4
-size 3438354725
+oid sha256:d809797a60aeed61eb98f88d0c36846d1b05285815e0d3e0e26ad8410e42d1f5
+size 3438366373

unet/diffusion_pytorch_model.fp16.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30eb3dc47c90e4a55476332b284b2331774c530edbbb83b70cacdd9e7b91af92
+oid sha256:914513b197e7d66b4aa00320d58cd284c7c8f28edb500268eb46b3710ed48832
 size 1719327893

unet/diffusion_pytorch_model.fp16.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c83908253f9a64d08c25fc90874c9c8aef9a329ce1ca5fb909d73b0c83d1ea21
+oid sha256:63c7f3d6ffa1f0d585574f43b595bed2620c65c303f27aaaa89bb57e3d266928
 size 1719125304

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19da7aaa4b880e59d56843f1fcb4dd9b599c28a1d9d9af7c1143057c8ffae9f1
-size 3438167540
+oid sha256:a8c9acb3b65f70f89f59ef1ceb2ab372a499ca4c925552b4dda0aa2a29cfb7c1
+size 3438167536

vae/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.6.0",
+  "_diffusers_version": "0.18.0.dev0",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -20,6 +20,7 @@
   "norm_num_groups": 32,
   "out_channels": 3,
   "sample_size": 512,
+  "scaling_factor": 0.18215,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",

vae/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b134cded8eb78b184aefb8805b6b572f36fa77b255c483665dda931fa0130c5
-size 334707217
+oid sha256:8bc6d71b9f9ec957f9406202eda0c9e17117ccb5b4bbdb1cc0c3ead413029d90
+size 334712113

vae/diffusion_pytorch_model.fp16.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7643b3e40b9f128eda5fe174fea73c3ef3903562651fb344a79439709c2e503
+oid sha256:cbfc384b11302ff776741bc6d0091283c4d26b79755c5c8ba241fdadfe67b538
 size 167405651

vae/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a08607e9d4f473d67a63070490db0c1e95b50d94789dc02b63851ace9a79d44
+size 167335342

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d10ca1960f9f889bf2256b2fafec29e8ead742967d5a34b635549437bcc9b825
+size 334643268