Add Diffusers Weights (#5)

depth_estimator/config.json

@@ -0,0 +1,460 @@
+{
+  "_commit_hash": "65776c96786d3dd82c1cdb4847ea0c2cb46a943c",
+  "_name_or_path": "Intel/dpt-hybrid-midas",
+  "architectures": [
+    "DPTForDepthEstimation"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auxiliary_loss_weight": 0.4,
+  "backbone_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "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,
+    "depths": [
+      3,
+      4,
+      9
+    ],
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.0,
+    "early_stopping": false,
+    "embedding_dynamic_padding": true,
+    "embedding_size": 64,
+    "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,
+    "global_padding": "SAME",
+    "hidden_act": "relu",
+    "hidden_sizes": [
+      256,
+      512,
+      1024,
+      2048
+    ],
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_type": "bottleneck",
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "bit",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_groups": 32,
+    "num_return_sequences": 1,
+    "out_features": [
+      "stage1",
+      "stage2",
+      "stage3"
+    ],
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "output_stride": 32,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3"
+    ],
+    "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": "4.26.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "width_factor": 1
+  },
+  "backbone_featmap_shape": [
+    1,
+    1024,
+    24,
+    24
+  ],
+  "backbone_out_indices": [
+    2,
+    5,
+    8,
+    11
+  ],
+  "fusion_hidden_size": 256,
+  "head_in_index": -1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29",
+    "30": "LABEL_30",
+    "31": "LABEL_31",
+    "32": "LABEL_32",
+    "33": "LABEL_33",
+    "34": "LABEL_34",
+    "35": "LABEL_35",
+    "36": "LABEL_36",
+    "37": "LABEL_37",
+    "38": "LABEL_38",
+    "39": "LABEL_39",
+    "40": "LABEL_40",
+    "41": "LABEL_41",
+    "42": "LABEL_42",
+    "43": "LABEL_43",
+    "44": "LABEL_44",
+    "45": "LABEL_45",
+    "46": "LABEL_46",
+    "47": "LABEL_47",
+    "48": "LABEL_48",
+    "49": "LABEL_49",
+    "50": "LABEL_50",
+    "51": "LABEL_51",
+    "52": "LABEL_52",
+    "53": "LABEL_53",
+    "54": "LABEL_54",
+    "55": "LABEL_55",
+    "56": "LABEL_56",
+    "57": "LABEL_57",
+    "58": "LABEL_58",
+    "59": "LABEL_59",
+    "60": "LABEL_60",
+    "61": "LABEL_61",
+    "62": "LABEL_62",
+    "63": "LABEL_63",
+    "64": "LABEL_64",
+    "65": "LABEL_65",
+    "66": "LABEL_66",
+    "67": "LABEL_67",
+    "68": "LABEL_68",
+    "69": "LABEL_69",
+    "70": "LABEL_70",
+    "71": "LABEL_71",
+    "72": "LABEL_72",
+    "73": "LABEL_73",
+    "74": "LABEL_74",
+    "75": "LABEL_75",
+    "76": "LABEL_76",
+    "77": "LABEL_77",
+    "78": "LABEL_78",
+    "79": "LABEL_79",
+    "80": "LABEL_80",
+    "81": "LABEL_81",
+    "82": "LABEL_82",
+    "83": "LABEL_83",
+    "84": "LABEL_84",
+    "85": "LABEL_85",
+    "86": "LABEL_86",
+    "87": "LABEL_87",
+    "88": "LABEL_88",
+    "89": "LABEL_89",
+    "90": "LABEL_90",
+    "91": "LABEL_91",
+    "92": "LABEL_92",
+    "93": "LABEL_93",
+    "94": "LABEL_94",
+    "95": "LABEL_95",
+    "96": "LABEL_96",
+    "97": "LABEL_97",
+    "98": "LABEL_98",
+    "99": "LABEL_99",
+    "100": "LABEL_100",
+    "101": "LABEL_101",
+    "102": "LABEL_102",
+    "103": "LABEL_103",
+    "104": "LABEL_104",
+    "105": "LABEL_105",
+    "106": "LABEL_106",
+    "107": "LABEL_107",
+    "108": "LABEL_108",
+    "109": "LABEL_109",
+    "110": "LABEL_110",
+    "111": "LABEL_111",
+    "112": "LABEL_112",
+    "113": "LABEL_113",
+    "114": "LABEL_114",
+    "115": "LABEL_115",
+    "116": "LABEL_116",
+    "117": "LABEL_117",
+    "118": "LABEL_118",
+    "119": "LABEL_119",
+    "120": "LABEL_120",
+    "121": "LABEL_121",
+    "122": "LABEL_122",
+    "123": "LABEL_123",
+    "124": "LABEL_124",
+    "125": "LABEL_125",
+    "126": "LABEL_126",
+    "127": "LABEL_127",
+    "128": "LABEL_128",
+    "129": "LABEL_129",
+    "130": "LABEL_130",
+    "131": "LABEL_131",
+    "132": "LABEL_132",
+    "133": "LABEL_133",
+    "134": "LABEL_134",
+    "135": "LABEL_135",
+    "136": "LABEL_136",
+    "137": "LABEL_137",
+    "138": "LABEL_138",
+    "139": "LABEL_139",
+    "140": "LABEL_140",
+    "141": "LABEL_141",
+    "142": "LABEL_142",
+    "143": "LABEL_143",
+    "144": "LABEL_144",
+    "145": "LABEL_145",
+    "146": "LABEL_146",
+    "147": "LABEL_147",
+    "148": "LABEL_148",
+    "149": "LABEL_149"
+  },
+  "image_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_hybrid": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_100": 100,
+    "LABEL_101": 101,
+    "LABEL_102": 102,
+    "LABEL_103": 103,
+    "LABEL_104": 104,
+    "LABEL_105": 105,
+    "LABEL_106": 106,
+    "LABEL_107": 107,
+    "LABEL_108": 108,
+    "LABEL_109": 109,
+    "LABEL_11": 11,
+    "LABEL_110": 110,
+    "LABEL_111": 111,
+    "LABEL_112": 112,
+    "LABEL_113": 113,
+    "LABEL_114": 114,
+    "LABEL_115": 115,
+    "LABEL_116": 116,
+    "LABEL_117": 117,
+    "LABEL_118": 118,
+    "LABEL_119": 119,
+    "LABEL_12": 12,
+    "LABEL_120": 120,
+    "LABEL_121": 121,
+    "LABEL_122": 122,
+    "LABEL_123": 123,
+    "LABEL_124": 124,
+    "LABEL_125": 125,
+    "LABEL_126": 126,
+    "LABEL_127": 127,
+    "LABEL_128": 128,
+    "LABEL_129": 129,
+    "LABEL_13": 13,
+    "LABEL_130": 130,
+    "LABEL_131": 131,
+    "LABEL_132": 132,
+    "LABEL_133": 133,
+    "LABEL_134": 134,
+    "LABEL_135": 135,
+    "LABEL_136": 136,
+    "LABEL_137": 137,
+    "LABEL_138": 138,
+    "LABEL_139": 139,
+    "LABEL_14": 14,
+    "LABEL_140": 140,
+    "LABEL_141": 141,
+    "LABEL_142": 142,
+    "LABEL_143": 143,
+    "LABEL_144": 144,
+    "LABEL_145": 145,
+    "LABEL_146": 146,
+    "LABEL_147": 147,
+    "LABEL_148": 148,
+    "LABEL_149": 149,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_31": 31,
+    "LABEL_32": 32,
+    "LABEL_33": 33,
+    "LABEL_34": 34,
+    "LABEL_35": 35,
+    "LABEL_36": 36,
+    "LABEL_37": 37,
+    "LABEL_38": 38,
+    "LABEL_39": 39,
+    "LABEL_4": 4,
+    "LABEL_40": 40,
+    "LABEL_41": 41,
+    "LABEL_42": 42,
+    "LABEL_43": 43,
+    "LABEL_44": 44,
+    "LABEL_45": 45,
+    "LABEL_46": 46,
+    "LABEL_47": 47,
+    "LABEL_48": 48,
+    "LABEL_49": 49,
+    "LABEL_5": 5,
+    "LABEL_50": 50,
+    "LABEL_51": 51,
+    "LABEL_52": 52,
+    "LABEL_53": 53,
+    "LABEL_54": 54,
+    "LABEL_55": 55,
+    "LABEL_56": 56,
+    "LABEL_57": 57,
+    "LABEL_58": 58,
+    "LABEL_59": 59,
+    "LABEL_6": 6,
+    "LABEL_60": 60,
+    "LABEL_61": 61,
+    "LABEL_62": 62,
+    "LABEL_63": 63,
+    "LABEL_64": 64,
+    "LABEL_65": 65,
+    "LABEL_66": 66,
+    "LABEL_67": 67,
+    "LABEL_68": 68,
+    "LABEL_69": 69,
+    "LABEL_7": 7,
+    "LABEL_70": 70,
+    "LABEL_71": 71,
+    "LABEL_72": 72,
+    "LABEL_73": 73,
+    "LABEL_74": 74,
+    "LABEL_75": 75,
+    "LABEL_76": 76,
+    "LABEL_77": 77,
+    "LABEL_78": 78,
+    "LABEL_79": 79,
+    "LABEL_8": 8,
+    "LABEL_80": 80,
+    "LABEL_81": 81,
+    "LABEL_82": 82,
+    "LABEL_83": 83,
+    "LABEL_84": 84,
+    "LABEL_85": 85,
+    "LABEL_86": 86,
+    "LABEL_87": 87,
+    "LABEL_88": 88,
+    "LABEL_89": 89,
+    "LABEL_9": 9,
+    "LABEL_90": 90,
+    "LABEL_91": 91,
+    "LABEL_92": 92,
+    "LABEL_93": 93,
+    "LABEL_94": 94,
+    "LABEL_95": 95,
+    "LABEL_96": 96,
+    "LABEL_97": 97,
+    "LABEL_98": 98,
+    "LABEL_99": 99
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "dpt",
+  "neck_hidden_sizes": [
+    256,
+    512,
+    768,
+    768
+  ],
+  "neck_ignore_stages": [
+    0,
+    1
+  ],
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "qkv_bias": true,
+  "readout_type": "project",
+  "reassemble_factors": [
+    1,
+    1,
+    1,
+    0.5
+  ],
+  "semantic_classifier_dropout": 0.1,
+  "semantic_loss_ignore_index": 255,
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "use_auxiliary_head": true,
+  "use_batch_norm_in_fusion_residual": false
+}

depth_estimator/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c4d44f9d96ca3fa76dd3bbb153989a60b4ad5526559f3c598562a368d687ec
+size 489648389

feature_extractor/preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "ensure_multiple_of": 1,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "DPTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "keep_aspect_ratio": false,
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 384,
+    "width": 384
+  }
+}

model_index.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "StableDiffusionDepth2ImgPipeline",
+  "_diffusers_version": "0.10.0.dev0",
+  "depth_estimator": [
+    "transformers",
+    "DPTForDepthEstimation"
+  ],
+  "feature_extractor": [
+    "transformers",
+    "DPTImageProcessor"
+  ],
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,14 @@
+{
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.10.0.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,
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/diffusers/models--fusing--sd-depth-test/snapshots/200d326f1f39e1df3ffc78f7f0323c54fd68bdb6/text_encoder",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 23,
+  "pad_token_id": 1,
+  "projection_dim": 512,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0.dev0",
+  "vocab_size": 49408
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3e254d7b61353497ea0be2c4013df4ea8f739ee88cffa0ba58cd085459ed565
+size 1361671895

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": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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,
+  "name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/diffusers/models--fusing--sd-depth-test/snapshots/200d326f1f39e1df3ffc78f7f0323c54fd68bdb6/tokenizer",
+  "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
+  }
+}

unet/config.json

@@ -0,0 +1,46 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.10.0.dev0",
+  "_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/diffusers/models--fusing--sd-depth-test/snapshots/200d326f1f39e1df3ffc78f7f0323c54fd68bdb6/unet",
+  "act_fn": "silu",
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "cross_attention_dim": 1024,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 5,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "sample_size": 32,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "use_linear_projection": true
+}

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:871e132e8cbc029660523a057acd756b3dec68720dcff0601475ca34d9c65cb6
+size 3463924965

vae/config.json

@@ -0,0 +1,30 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.10.0.dev0",
+  "_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/diffusers/models--fusing--sd-depth-test/snapshots/200d326f1f39e1df3ffc78f7f0323c54fd68bdb6/vae",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 256,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b4889b6b1d4ce7ae320a02dedaeff1780ad77d415ea0d744b476155c6377ddc
+size 334707217