Upload folder using huggingface_hub

audio_mesher/config.json

@@ -0,0 +1,81 @@
+{
+  "_class_name": "Audio2MeshModel",
+  "_diffusers_version": "0.26.1",
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_normalize": true,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "feature_size": 1,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "latent_dim": 512,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_prob": 0.05,
+  "model_type": "wav2vec2",
+  "num_attention_heads": 12,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "num_negatives": 100,
+  "out_dim": 1404,
+  "pad_token_id": 0,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "proj_codevector_dim": 256,
+  "return_attention_mask": false,
+  "sampling_rate": 16000,
+  "use_final_features": true,
+  "vocab_size": 32
+}

audio_mesher/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2acdbba35b4d32b46b86628f773703492b7c1876d3454460ae2a9d2b07b1e9f
+size 190998344

denoising_unet/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet3DConditionModel",
+  "_diffusers_version": "0.26.1",
+  "act_fn": "silu",
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "cross_attention_dim": 768,
+  "down_block_types": [
+    "CrossAttnDownBlock3D",
+    "CrossAttnDownBlock3D",
+    "CrossAttnDownBlock3D",
+    "DownBlock3D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock3DCrossAttn",
+  "motion_module_decoder_only": false,
+  "motion_module_kwargs": {
+    "attention_block_types": [
+      "Temporal_Self",
+      "Temporal_Self"
+    ],
+    "num_attention_heads": 8,
+    "num_transformer_block": 1,
+    "temporal_attention_dim_div": 1,
+    "temporal_position_encoding": true,
+    "temporal_position_encoding_max_len": 32
+  },
+  "motion_module_mid_block": true,
+  "motion_module_resolutions": [
+    1,
+    2,
+    4,
+    8
+  ],
+  "motion_module_type": "Vanilla",
+  "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,
+  "unet_use_cross_frame_attention": false,
+  "unet_use_temporal_attention": false,
+  "up_block_types": [
+    "UpBlock3D",
+    "CrossAttnUpBlock3D",
+    "CrossAttnUpBlock3D",
+    "CrossAttnUpBlock3D"
+  ],
+  "upcast_attention": false,
+  "use_inflated_groupnorm": true,
+  "use_linear_projection": false,
+  "use_motion_module": true
+}

denoising_unet/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57f83ad9f45198ae5df7e9a8f85edcdae9c717baf0ec8bc7ac2c722c867506fb
+size 2628056032

image_encoder/config.json

@@ -0,0 +1,22 @@
+{
+  "architectures": [
+    "CLIPVisionModelWithProjection"
+  ],
+  "attention_dropout": 0,
+  "dropout": 0,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 1024,
+  "image_size": 224,
+  "initializer_factor": 1,
+  "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": "4.39.0"
+}

image_encoder/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dd0c1777bb75e2e9b7aa29b799b3ee8ebaaaa731e2c471a9ec589f12542cce7
+size 607980096

model_index.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "AniPortraitPipeline",
+  "_diffusers_version": "0.26.1",
+  "audio_mesher": [
+    "aniportrait.audio_models.audio2mesh",
+    "Audio2MeshModel"
+  ],
+  "denoising_unet": [
+    "aniportrait.models.unet_3d_condition",
+    "UNet3DConditionModel"
+  ],
+  "image_encoder": [
+    "transformers",
+    "CLIPVisionModelWithProjection"
+  ],
+  "pose_guider": [
+    "aniportrait.models.pose_guider",
+    "PoseGuiderModel"
+  ],
+  "reference_unet": [
+    "aniportrait.models.unet_2d_condition",
+    "UNet2DConditionModel"
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

pose_guider/config.json

@@ -0,0 +1,6 @@
+{
+  "_class_name": "PoseGuiderModel",
+  "_diffusers_version": "0.26.1",
+  "noise_latent_channels": 320,
+  "use_ca": true
+}

pose_guider/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e87d4bcbbf6299d7e10a6d9181911d6e8021401eada14b56eb62f02bc392b92
+size 335075930

reference_unet/config.json

@@ -0,0 +1,67 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.26.1",
+  "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,
+  "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": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "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
+}

reference_unet/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20b990bfd0b794e654818d27b66de6601aa679d40d6a2912ec6d72c6f13b7900
+size 1719100656

scheduler/scheduler_config.json

@@ -0,0 +1,19 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.26.1",
+  "beta_end": 0.012,
+  "beta_schedule": "linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "rescale_betas_zero_snr": true,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": true,
+  "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "trailing",
+  "trained_betas": null
+}

vae/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.26.1",
+  "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": 256,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
+size 167335342