Upload StableDiffusionPipeline

feature_extractor/preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "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,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

model_index.json

@@ -0,0 +1,34 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.21.0.dev0",
+  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
+  ],
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

safety_checker/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/home/hasnymarta/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/133a221b8aa7292a167afc5127cb63fb5005638b/safety_checker",
+  "architectures": [
+    "StableDiffusionSafetyChecker"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "dropout": 0.0,
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "model_type": "clip_text_model",
+    "num_attention_heads": 12
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.32.1",
+  "vision_config": {
+    "dropout": 0.0,
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14
+  }
+}

safety_checker/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57ecdfa243b170f9b4cb3eefaf0f64552ef78fc0bf0eb1c5b9675308447184f6
+size 608016280

scheduler/scheduler_config.json

@@ -0,0 +1,15 @@
+{
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.21.0.dev0",
+  "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,
+  "timestep_spacing": "leading",
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/home/hasnymarta/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/133a221b8aa7292a167afc5127cb63fb5005638b/text_encoder",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 512,
+  "torch_dtype": "float16",
+  "transformers_version": "4.32.1",
+  "vocab_size": 49536
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2f38fb9ad8c34c28f54c2b0c5e7b8846cf849abeb85fe6cbc8e61f696fdcc80
+size 246340760

tokenizer/added_tokens.json

@@ -0,0 +1,130 @@
+{
+  "<ad-brain-mri>": 49472,
+  "<ad-brain-mri>_1": 49473,
+  "<ad-brain-mri>_10": 49482,
+  "<ad-brain-mri>_11": 49483,
+  "<ad-brain-mri>_12": 49484,
+  "<ad-brain-mri>_13": 49485,
+  "<ad-brain-mri>_14": 49486,
+  "<ad-brain-mri>_15": 49487,
+  "<ad-brain-mri>_16": 49488,
+  "<ad-brain-mri>_17": 49489,
+  "<ad-brain-mri>_18": 49490,
+  "<ad-brain-mri>_19": 49491,
+  "<ad-brain-mri>_2": 49474,
+  "<ad-brain-mri>_20": 49492,
+  "<ad-brain-mri>_21": 49493,
+  "<ad-brain-mri>_22": 49494,
+  "<ad-brain-mri>_23": 49495,
+  "<ad-brain-mri>_24": 49496,
+  "<ad-brain-mri>_25": 49497,
+  "<ad-brain-mri>_26": 49498,
+  "<ad-brain-mri>_27": 49499,
+  "<ad-brain-mri>_28": 49500,
+  "<ad-brain-mri>_29": 49501,
+  "<ad-brain-mri>_3": 49475,
+  "<ad-brain-mri>_30": 49502,
+  "<ad-brain-mri>_31": 49503,
+  "<ad-brain-mri>_32": 49504,
+  "<ad-brain-mri>_33": 49505,
+  "<ad-brain-mri>_34": 49506,
+  "<ad-brain-mri>_35": 49507,
+  "<ad-brain-mri>_36": 49508,
+  "<ad-brain-mri>_37": 49509,
+  "<ad-brain-mri>_38": 49510,
+  "<ad-brain-mri>_39": 49511,
+  "<ad-brain-mri>_4": 49476,
+  "<ad-brain-mri>_40": 49512,
+  "<ad-brain-mri>_41": 49513,
+  "<ad-brain-mri>_42": 49514,
+  "<ad-brain-mri>_43": 49515,
+  "<ad-brain-mri>_44": 49516,
+  "<ad-brain-mri>_45": 49517,
+  "<ad-brain-mri>_46": 49518,
+  "<ad-brain-mri>_47": 49519,
+  "<ad-brain-mri>_48": 49520,
+  "<ad-brain-mri>_49": 49521,
+  "<ad-brain-mri>_5": 49477,
+  "<ad-brain-mri>_50": 49522,
+  "<ad-brain-mri>_51": 49523,
+  "<ad-brain-mri>_52": 49524,
+  "<ad-brain-mri>_53": 49525,
+  "<ad-brain-mri>_54": 49526,
+  "<ad-brain-mri>_55": 49527,
+  "<ad-brain-mri>_56": 49528,
+  "<ad-brain-mri>_57": 49529,
+  "<ad-brain-mri>_58": 49530,
+  "<ad-brain-mri>_59": 49531,
+  "<ad-brain-mri>_6": 49478,
+  "<ad-brain-mri>_60": 49532,
+  "<ad-brain-mri>_61": 49533,
+  "<ad-brain-mri>_62": 49534,
+  "<ad-brain-mri>_63": 49535,
+  "<ad-brain-mri>_7": 49479,
+  "<ad-brain-mri>_8": 49480,
+  "<ad-brain-mri>_9": 49481,
+  "<cn-brain-mri>": 49408,
+  "<cn-brain-mri>_1": 49409,
+  "<cn-brain-mri>_10": 49418,
+  "<cn-brain-mri>_11": 49419,
+  "<cn-brain-mri>_12": 49420,
+  "<cn-brain-mri>_13": 49421,
+  "<cn-brain-mri>_14": 49422,
+  "<cn-brain-mri>_15": 49423,
+  "<cn-brain-mri>_16": 49424,
+  "<cn-brain-mri>_17": 49425,
+  "<cn-brain-mri>_18": 49426,
+  "<cn-brain-mri>_19": 49427,
+  "<cn-brain-mri>_2": 49410,
+  "<cn-brain-mri>_20": 49428,
+  "<cn-brain-mri>_21": 49429,
+  "<cn-brain-mri>_22": 49430,
+  "<cn-brain-mri>_23": 49431,
+  "<cn-brain-mri>_24": 49432,
+  "<cn-brain-mri>_25": 49433,
+  "<cn-brain-mri>_26": 49434,
+  "<cn-brain-mri>_27": 49435,
+  "<cn-brain-mri>_28": 49436,
+  "<cn-brain-mri>_29": 49437,
+  "<cn-brain-mri>_3": 49411,
+  "<cn-brain-mri>_30": 49438,
+  "<cn-brain-mri>_31": 49439,
+  "<cn-brain-mri>_32": 49440,
+  "<cn-brain-mri>_33": 49441,
+  "<cn-brain-mri>_34": 49442,
+  "<cn-brain-mri>_35": 49443,
+  "<cn-brain-mri>_36": 49444,
+  "<cn-brain-mri>_37": 49445,
+  "<cn-brain-mri>_38": 49446,
+  "<cn-brain-mri>_39": 49447,
+  "<cn-brain-mri>_4": 49412,
+  "<cn-brain-mri>_40": 49448,
+  "<cn-brain-mri>_41": 49449,
+  "<cn-brain-mri>_42": 49450,
+  "<cn-brain-mri>_43": 49451,
+  "<cn-brain-mri>_44": 49452,
+  "<cn-brain-mri>_45": 49453,
+  "<cn-brain-mri>_46": 49454,
+  "<cn-brain-mri>_47": 49455,
+  "<cn-brain-mri>_48": 49456,
+  "<cn-brain-mri>_49": 49457,
+  "<cn-brain-mri>_5": 49413,
+  "<cn-brain-mri>_50": 49458,
+  "<cn-brain-mri>_51": 49459,
+  "<cn-brain-mri>_52": 49460,
+  "<cn-brain-mri>_53": 49461,
+  "<cn-brain-mri>_54": 49462,
+  "<cn-brain-mri>_55": 49463,
+  "<cn-brain-mri>_56": 49464,
+  "<cn-brain-mri>_57": 49465,
+  "<cn-brain-mri>_58": 49466,
+  "<cn-brain-mri>_59": 49467,
+  "<cn-brain-mri>_6": 49414,
+  "<cn-brain-mri>_60": 49468,
+  "<cn-brain-mri>_61": 49469,
+  "<cn-brain-mri>_62": 49470,
+  "<cn-brain-mri>_63": 49471,
+  "<cn-brain-mri>_7": 49415,
+  "<cn-brain-mri>_8": 49416,
+  "<cn-brain-mri>_9": 49417
+}

tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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
+  }
+}

unet/config.json

@@ -0,0 +1,66 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.21.0.dev0",
+  "_name_or_path": "/home/hasnymarta/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/133a221b8aa7292a167afc5127cb63fb5005638b/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": [
+    320,
+    640,
+    1280,
+    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",
+    "CrossAttnDownBlock2D",
+    "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,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "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:a35404d03ec8f977715a4d2a080ddf72e2144f2ee49bb1ee213258bc64f9cc87
+size 1719125304

vae/config.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.21.0.dev0",
+  "_name_or_path": "/home/hasnymarta/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/133a221b8aa7292a167afc5127cb63fb5005638b/vae",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "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",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c
+size 167335342