Upload 10 files

feature_extractor_1/preprocessor_config.json

@@ -0,0 +1,44 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_center_crop",
+    "crop_size",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_convert_rgb",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "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_1/config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "/mnt/pfs/users/dengken/hugging_face/models--facebook--dinov2-large/snapshots/47b73eefe95e8d44ec3623f8890bd894b6ea2d6c",
+  "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": "float32",
+  "transformers_version": "4.41.0",
+  "use_swiglu_ffn": false
+}

image_encoder_1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:399fba97a95f22c36834418bc69373364a99af3a1153da1c0fb31db567c92e23
+size 1217522888

model_index.json

@@ -0,0 +1,28 @@
+{
+  "_class_name": "DetailGen3DPipeline",
+  "_diffusers_version": "0.32.0.dev0",
+  "feature_extractor_1": [
+    "transformers",
+    "BitImageProcessor"
+  ],
+  "image_encoder_1": [
+    "transformers",
+    "Dinov2Model"
+  ],
+  "noise_scheduler": [
+    "diffusers",
+    "DDPMScheduler"
+  ],
+  "scheduler": [
+    "detailgen3d.schedulers.scheduling_rectified_flow",
+    "RectifiedFlowScheduler"
+  ],
+  "transformer": [
+    "detailgen3d.models.transformers.detailgen3d_transformers",
+    "DetailGen3DDiTModel"
+  ],
+  "vae": [
+    "detailgen3d.models.autoencoders.autoencoder_kl_triposg",
+    "TripoSGVAEModel"
+  ]
+}

noise_scheduler/scheduler_config.json

@@ -0,0 +1,19 @@
+{
+  "_class_name": "DDPMScheduler",
+  "_diffusers_version": "0.32.0.dev0",
+  "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,
+  "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "leading",
+  "trained_betas": null,
+  "variance_type": "fixed_small"
+}

scheduler/scheduler_config.json

@@ -0,0 +1,7 @@
+{
+  "_class_name": "RectifiedFlowScheduler",
+  "_diffusers_version": "0.32.0.dev0",
+  "num_train_timesteps": 1000,
+  "shift": 1.0,
+  "use_dynamic_shifting": false
+}

transformer/config.json

@@ -0,0 +1,9 @@
+{
+  "_class_name": "DetailGen3DDiTModel",
+  "_diffusers_version": "0.32.0.dev0",
+  "cross_attention_dim": 1024,
+  "in_channels": 64,
+  "num_attention_heads": 12,
+  "num_layers": 24,
+  "width": 768
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcc7abf6b049b91d8e4a93e8914a1df819b3f8edc352cdce67054e251f3a2c5f
+size 1474293920

vae/config.json

@@ -0,0 +1,14 @@
+{
+  "_class_name": "Tripo2VAEModel",
+  "_diffusers_version": "0.32.0.dev0",
+  "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 sha256:488d39edc7a7d3cd4d94baea243c4ed583ed830b3b5f0ae781ad6a00aa8d7369
+size 970685468