Delete folder ./mvd_std with huggingface_hub

mvd_std/feature_extractor_vae/preprocessor_config.json

@@ -1,19 +0,0 @@
-{
-  "crop_size": {
-    "height": 512,
-    "width": 512
-  },
-  "do_center_crop": true,
-  "do_convert_rgb": true,
-  "do_normalize": true,
-  "do_rescale": true,
-  "do_resize": true,
-  "image_mean": 0.5,
-  "image_processor_type": "CLIPImageProcessor",
-  "image_std": 0.5,
-  "resample": 2,
-  "rescale_factor": 0.00392156862745098,
-  "size": {
-    "shortest_edge": 512
-  }
-}

mvd_std/model_index.json

@@ -1,116 +0,0 @@
-{
-  "_class_name": "HunYuan3DMVDPipeline",
-  "_diffusers_version": "0.20.0",
-  "_name_or_path": "./hunyuan3d/v72_s22k",
-  "feature_extractor_vae": [
-    "transformers",
-    "CLIPImageProcessor"
-  ],
-  "ramping_coefficients": [
-    0.00301829120144248,
-    0.2204633206129074,
-    0.21527841687202454,
-    0.23498539626598358,
-    0.1914631873369217,
-    0.20188239216804504,
-    0.19352824985980988,
-    0.17249998450279236,
-    0.15826298296451569,
-    0.15236389636993408,
-    0.13444548845291138,
-    0.12044154852628708,
-    0.12808501720428467,
-    0.1271015852689743,
-    0.13629068434238434,
-    0.14516159892082214,
-    0.15645112097263336,
-    0.16885493695735931,
-    0.18022602796554565,
-    0.1958882212638855,
-    0.21415705978870392,
-    0.23056700825691223,
-    0.2505834102630615,
-    0.2574525773525238,
-    0.275470107793808,
-    0.2808215022087097,
-    0.29953837394714355,
-    0.2967497408390045,
-    0.2883710563182831,
-    0.3023308515548706,
-    0.3054688572883606,
-    0.32596179842948914,
-    0.3225354254245758,
-    0.3140765428543091,
-    0.3288663625717163,
-    0.3435625731945038,
-    0.3342442810535431,
-    0.32937031984329224,
-    0.35734811425209045,
-    0.3601177930831909,
-    0.3517529368400574,
-    0.3810708224773407,
-    0.40007662773132324,
-    0.4264647364616394,
-    0.3977527916431427,
-    0.4314143657684326,
-    0.49558719992637634,
-    0.4665665030479431,
-    0.48960328102111816,
-    0.5141982436180115,
-    0.5230164527893066,
-    0.5266074538230896,
-    0.5456079840660095,
-    0.5737904906272888,
-    0.5882097482681274,
-    0.6210350394248962,
-    0.6530380845069885,
-    0.6383244395256042,
-    0.6792004704475403,
-    0.6567418575286865,
-    0.7517656683921814,
-    0.736494243144989,
-    0.7586457133293152,
-    0.8130561709403992,
-    0.9578766226768494,
-    1.001284122467041,
-    0.9404520988464355,
-    1.004292368888855,
-    0.9145274758338928,
-    0.9771682620048523,
-    1.0350638628005981,
-    1.0265849828720093,
-    1.0594775676727295,
-    0.980824887752533,
-    1.0715670585632324,
-    1.0140161514282227,
-    1.1983819007873535
-  ],
-  "safety_checker": [
-    null,
-    null
-  ],
-  "scheduler": [
-    "diffusers",
-    "EulerAncestralDiscreteScheduler"
-  ],
-  "unet": [
-    "diffusers",
-    "UNet2DConditionModel"
-  ],
-  "vae": [
-    "diffusers",
-    "AutoencoderKL"
-  ],
-  "vision_encoder": [
-    "transformers",
-    "CLIPVisionModelWithProjection"
-  ],
-  "vision_encoder_2": [
-    "transformers",
-    "CLIPVisionModelWithProjection"
-  ],
-  "vision_processor": [
-    "transformers",
-    "CLIPImageProcessor"
-  ]
-}

mvd_std/scheduler/scheduler_config.json

@@ -1,16 +0,0 @@
-{
-  "_class_name": "EulerAncestralDiscreteScheduler",
-  "_diffusers_version": "0.20.0",
-  "beta_end": 0.012,
-  "beta_schedule": "linear",
-  "beta_start": 0.00085,
-  "clip_sample": false,
-  "num_train_timesteps": 1000,
-  "prediction_type": "epsilon",
-  "rescale_betas_zero_snr": false,
-  "set_alpha_to_one": false,
-  "skip_prk_steps": true,
-  "steps_offset": 1,
-  "timestep_spacing": "trailing",
-  "trained_betas": null
-}

mvd_std/uc_text_emb.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:30b66304d244a8c1bb2f8e4047710da9fe249d9c4bcacdae909a1b23c084e9a0
-size 631543

mvd_std/uc_text_emb_2.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c86259792b6f0c6efadd1fbebc6b735d93e62b4f4f77555550971e3648a52ebe
-size 5885

mvd_std/unet/config.json

@@ -1,73 +0,0 @@
-{
-  "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.20.0",
-  "_name_or_path": "./hunyuan3d/v72_s22k/unet",
-  "act_fn": "silu",
-  "addition_embed_type": "text_time",
-  "addition_embed_type_num_heads": 64,
-  "addition_time_embed_dim": 256,
-  "attention_head_dim": [
-    5,
-    10,
-    20
-  ],
-  "attention_type": "default",
-  "block_out_channels": [
-    320,
-    640,
-    1280
-  ],
-  "center_input_sample": false,
-  "class_embed_type": null,
-  "class_embeddings_concat": false,
-  "conv_in_kernel": 3,
-  "conv_out_kernel": 3,
-  "cross_attention_dim": 2048,
-  "cross_attention_norm": null,
-  "down_block_types": [
-    "DownBlock2D",
-    "CrossAttnDownBlock2D",
-    "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,
-  "projection_class_embeddings_input_dim": 2816,
-  "resnet_out_scale_factor": 1.0,
-  "resnet_skip_time_act": false,
-  "resnet_time_scale_shift": "default",
-  "reverse_transformer_layers_per_block": null,
-  "sample_size": 128,
-  "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,
-    2,
-    10
-  ],
-  "up_block_types": [
-    "CrossAttnUpBlock2D",
-    "CrossAttnUpBlock2D",
-    "UpBlock2D"
-  ],
-  "upcast_attention": null,
-  "use_linear_projection": true
-}

mvd_std/unet/diffusion_pytorch_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e687df99afd99a178d3ed8a8935951ae4484d4ac01d355668ddd9657807b02d0
-size 5135149760

mvd_std/vae/config.json

@@ -1,38 +0,0 @@
-{
-  "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.20.0",
-  "_name_or_path": "./hunyuan3d/v72_s22k/vae",
-  "act_fn": "silu",
-  "block_out_channels": [
-    128,
-    256,
-    512,
-    512
-  ],
-  "down_block_types": [
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D"
-  ],
-  "force_upcast": false,
-  "in_channels": 3,
-  "latent_channels": 4,
-  "latents_mean": null,
-  "latents_std": null,
-  "layers_per_block": 2,
-  "mid_block_add_attention": true,
-  "norm_num_groups": 32,
-  "out_channels": 3,
-  "sample_size": 512,
-  "scaling_factor": 0.13025,
-  "shift_factor": null,
-  "up_block_types": [
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D"
-  ],
-  "use_post_quant_conv": true,
-  "use_quant_conv": true
-}

mvd_std/vae/diffusion_pytorch_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48
-size 167335342

mvd_std/vision_encoder/config.json

@@ -1,23 +0,0 @@
-{
-  "_name_or_path": "./hunyuan3d/v72_s22k/vision_encoder",
-  "architectures": [
-    "CLIPVisionModelWithProjection"
-  ],
-  "attention_dropout": 0.0,
-  "dropout": 0.0,
-  "hidden_act": "quick_gelu",
-  "hidden_size": 1024,
-  "image_size": 224,
-  "initializer_factor": 1.0,
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "layer_norm_eps": 1e-05,
-  "model_type": "clip_vision_model",
-  "num_attention_heads": 16,
-  "num_channels": 3,
-  "num_hidden_layers": 24,
-  "patch_size": 14,
-  "projection_dim": 768,
-  "torch_dtype": "float16",
-  "transformers_version": "4.27.2"
-}

mvd_std/vision_encoder/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0839dc3a0f2899f9b85df8cd64b8acd1a3303a95f73a895aced7c31aee7d80cf
-size 607982256

mvd_std/vision_encoder_2/config.json

@@ -1,23 +0,0 @@
-{
-  "_name_or_path": "./hunyuan3d/v72_s22k/vision_encoder_2",
-  "architectures": [
-    "CLIPVisionModelWithProjection"
-  ],
-  "attention_dropout": 0.0,
-  "dropout": 0.0,
-  "hidden_act": "gelu",
-  "hidden_size": 1664,
-  "image_size": 224,
-  "initializer_factor": 1.0,
-  "initializer_range": 0.02,
-  "intermediate_size": 8192,
-  "layer_norm_eps": 1e-05,
-  "model_type": "clip_vision_model",
-  "num_attention_heads": 16,
-  "num_channels": 3,
-  "num_hidden_layers": 48,
-  "patch_size": 14,
-  "projection_dim": 1280,
-  "torch_dtype": "float16",
-  "transformers_version": "4.27.2"
-}

mvd_std/vision_encoder_2/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:657723e09f46a7c3957df651601029f66b1748afb12b419816330f16ed45d64d
-size 3689912664

mvd_std/vision_processor/preprocessor_config.json

@@ -1,27 +0,0 @@
-{
-  "crop_size": {
-    "height": 224,
-    "width": 224
-  },
-  "do_center_crop": true,
-  "do_convert_rgb": true,
-  "do_normalize": true,
-  "do_rescale": true,
-  "do_resize": true,
-  "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
-  }
-}