Add link to paper (#2)

- Add link to paper (0a3a2d6df7dcfb55d6885b3cd56a92827fe21f9e)


Co-authored-by: Niels Rogge <[email protected]>

README.md

@@ -4,226 +4,8 @@ library_name: diffusers
 pipeline_tag: image-to-3d
 ---
 
-# File information
+# SOAP: Style-Omniscient Animatable Portraits
 
-The repository contains the following file information:
-
-Filename: model_index.json
-Content: {
-  "_class_name": "MVDiffusionImagePipeline",
-  "_diffusers_version": "0.30.3",
-  "feature_extractor": [
-    "transformers",
-    "CLIPImageProcessor"
-  ],
-  "image_encoder": [
-    "transformers",
-    "CLIPVisionModelWithProjection"
-  ],
-  "requires_safety_checker": true,
-  "safety_checker": [
-    null,
-    null
-  ],
-  "scheduler": [
-    "diffusers",
-    "DDIMScheduler"
-  ],
-  "unet": [
-    "mv_unet",
-    "UnifieldWrappedUNet"
-  ],
-  "vae": [
-    "diffusers",
-    "AutoencoderKL"
-  ]
-}
-
-Filename: config.json
-Content: {
-  "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.30.3",
-  "_name_or_path": "Luffuly/unique3d-mvimage-diffuser",
-  "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,
-  "latents_mean": null,
-  "latents_std": null,
-  "layers_per_block": 2,
-  "mid_block_add_attention": true,
-  "norm_num_groups": 32,
-  "out_channels": 3,
-  "sample_size": 256,
-  "scaling_factor": 0.18215,
-  "shift_factor": null,
-  "up_block_types": [
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D"
-  ],
-  "use_post_quant_conv": true,
-  "use_quant_conv": true
-}
-
-Filename: scheduler_config.json
-Content: {
-  "_class_name": "DDIMScheduler",
-  "_diffusers_version": "0.30.3",
-  "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,
-  "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,
-  "steps_offset": 1,
-  "thresholding": false,
-  "timestep_spacing": "leading",
-  "trained_betas": null
-}
-
-Filename: config.json
-Content: {
-  "_class_name": "UnifieldWrappedUNet",
-  "_diffusers_version": "0.30.3",
-  "_name_or_path": "outputs/vroid-mvimage-6view/checkpoint",
-  "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": 8,
-  "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": 8,
-  "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"
-  ],
-  "n_views": 6,
-  "upcast_attention": false,
-  "use_linear_projection": false
-}
-
-Filename: preprocessor_config.json
-Content: {
-  "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
-  }
-}
-
-Filename: config.json
-Content: {
-  "_name_or_path": "Luffuly/unique3d-mvimage-diffuser",
-  "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": "4.45.2"
-}
-
-# Code: https://github.com/TingtingLiao/soap
+This repository contains the model of the paper [SOAP: Style-Omniscient Animatable Portraits](https://huggingface.co/papers/2505.05022).
+  
+Code: https://github.com/TingtingLiao/soap