Upload folder using huggingface_hub

README.md

@@ -1,3 +1,18 @@
----
-license: mit
----
+---
+license: mit
+pipeline_tag: image-to-3d
+tags:
+- partcrafter
+- 3d-generation
+- rectified-flow
+---
+# PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers (Scene Level)
+
+PartCrafter is a structured 3D generative model that jointly generates multiple parts and objects from a single RGB image in one shot.
+This HuggingFace🤗 repo stores pretrained model weights for PartCrafter on **scene level**. 
+
+For more details about usage, please refer to the [official GitHub repo](https://github.com/wgsxm/PartCrafter).
+
+- Project page: https://wgsxm.github.io/projects/partcrafter/
+- Code: https://github.com/wgsxm/PartCrafter
+- Paper: https://arxiv.org/abs/2506.05573

feature_extractor_dinov2/preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "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": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "BitImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 256
+  }
+}

image_encoder_dinov2/config.json

@@ -0,0 +1,60 @@
+{
+  "apply_layernorm": true,
+  "architectures": [
+    "Dinov2Model"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "drop_path_rate": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "image_size": 518,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-06,
+  "layerscale_value": 1.0,
+  "mlp_ratio": 4,
+  "model_type": "dinov2",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 24,
+  "out_features": [
+    "stage24"
+  ],
+  "out_indices": [
+    24
+  ],
+  "patch_size": 14,
+  "qkv_bias": true,
+  "reshape_hidden_states": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4",
+    "stage5",
+    "stage6",
+    "stage7",
+    "stage8",
+    "stage9",
+    "stage10",
+    "stage11",
+    "stage12",
+    "stage13",
+    "stage14",
+    "stage15",
+    "stage16",
+    "stage17",
+    "stage18",
+    "stage19",
+    "stage20",
+    "stage21",
+    "stage22",
+    "stage23",
+    "stage24"
+  ],
+  "torch_dtype": "float16",
+  "transformers_version": "4.53.2",
+  "use_mask_token": true,
+  "use_swiglu_ffn": false
+}

image_encoder_dinov2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa0b83921a3339259fb1ef684ce63c9d09b5a45f9998e0789a0ad4cba318b07b
+size 608785376

model_index.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "PartCrafterPipeline",
+  "_diffusers_version": "0.34.0",
+  "feature_extractor_dinov2": [
+    "transformers",
+    "BitImageProcessor"
+  ],
+  "image_encoder_dinov2": [
+    "transformers",
+    "Dinov2Model"
+  ],
+  "scheduler": [
+    "src.schedulers.scheduling_rectified_flow",
+    "RectifiedFlowScheduler"
+  ],
+  "transformer": [
+    "src.models.transformers.partcrafter_transformer",
+    "PartCrafterDiTModel"
+  ],
+  "vae": [
+    "src.models.autoencoders.autoencoder_kl_triposg",
+    "TripoSGVAEModel"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,7 @@
+{
+  "_class_name": "RectifiedFlowScheduler",
+  "_diffusers_version": "0.34.0",
+  "num_train_timesteps": 1000,
+  "shift": 1,
+  "use_dynamic_shifting": false
+}

transformer/config.json

@@ -0,0 +1,27 @@
+{
+  "_class_name": "PartCrafterDiTModel",
+  "_diffusers_version": "0.34.0",
+  "cross_attention_dim": 1024,
+  "enable_global_cross_attn": true,
+  "enable_local_cross_attn": true,
+  "enable_part_embedding": true,
+  "global_attn_block_id_range": null,
+  "global_attn_block_ids": [
+    0,
+    2,
+    4,
+    6,
+    8,
+    10,
+    12,
+    14,
+    16,
+    18,
+    20
+  ],
+  "in_channels": 64,
+  "max_num_parts": 32,
+  "num_attention_heads": 16,
+  "num_layers": 21,
+  "width": 2048
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da5522acb9098797dc2ead2c42b448adb1f5f25b0acda58c2dc36356cea82b7e
+size 2879298752

vae/config.json

@@ -0,0 +1,15 @@
+{
+  "_class_name": "TripoSGVAEModel",
+  "_diffusers_version": "0.34.0",
+  "_name_or_path": "pretrained_weights/TripoSG",
+  "embed_frequency": 8,
+  "embed_include_pi": false,
+  "embedding_type": "frequency",
+  "in_channels": 3,
+  "latent_channels": 64,
+  "num_attention_heads": 8,
+  "num_layers_decoder": 16,
+  "num_layers_encoder": 8,
+  "width_decoder": 1024,
+  "width_encoder": 512
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b43b006e5692223877427cdb568c2c1477f52a2d226db4d5eb354b4886c167a4
+size 485361378