Duplicate from VAST-AI/MIDI-3D

Co-authored-by: zehuan-huang <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+license: apache-2.0
+pipeline_tag: image-to-3d
+---
+
+# MIDI-3D
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+MIDI is a 3D generative model for single image to compositional 3D scene generation. It was introduced in the paper [MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation](https://huggingface.co/papers/2412.03558).
+
+Project page: https://huanngzh.github.io/MIDI-Page/
+
+Code: https://github.com/VAST-AI-Research/MIDI-3D

feature_extractor_1/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": [
+    0.48145466,
+    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
+  }
+}

feature_extractor_2/preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "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": [
+    0.485,
+    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": 512
+  }
+}

image_encoder_1/config.json

@@ -0,0 +1,22 @@
+{
+  "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": "bfloat16",
+  "transformers_version": "4.45.2"
+}

image_encoder_1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4b33d864f89a793357a768cb07d0dc18d6a14e6664f4110a0d535ca9ba78da8
+size 607980488

image_encoder_2/config.json

@@ -0,0 +1,59 @@
+{
+  "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": 7,
+  "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": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_swiglu_ffn": false
+}

image_encoder_2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a354885ca4601d0eb89aa2ec4f5a32a56a9e7a92c725c6faadb2f783b0bb65ba
+size 610391440

model_index.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "MIDIPipeline",
+  "_diffusers_version": "0.32.2",
+  "feature_extractor_1": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "feature_extractor_2": [
+    "transformers",
+    "BitImageProcessor"
+  ],
+  "image_encoder_1": [
+    "transformers",
+    "CLIPVisionModelWithProjection"
+  ],
+  "image_encoder_2": [
+    "transformers",
+    "Dinov2Model"
+  ],
+  "scheduler": [
+    "midi.schedulers.scheduling_rectified_flow",
+    "RectifiedFlowScheduler"
+  ],
+  "transformer": [
+    "midi.models.transformers.triposg_transformer",
+    "TripoSGDiTModel"
+  ],
+  "vae": [
+    "midi.models.autoencoders.autoencoder_kl_triposg",
+    "TripoSGVAEModel"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,7 @@
+{
+  "_class_name": "RectifiedFlowScheduler",
+  "_diffusers_version": "0.32.2",
+  "num_train_timesteps": 1000,
+  "shift": 2,
+  "use_dynamic_shifting": false
+}

transformer/config.json

@@ -0,0 +1,10 @@
+{
+  "_class_name": "TripoSGDiTModel",
+  "_diffusers_version": "0.32.2",
+  "cross_attention_2_dim": 1024,
+  "cross_attention_dim": 768,
+  "in_channels": 64,
+  "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 sha256:92c7177fa8f3a4b70b29b12c36725fee71c10b404f5cbe4edcdf1daa3c713b1b
+size 3363898656

vae/config.json

@@ -0,0 +1,14 @@
+{
+  "_class_name": "TripoSGVAEModel",
+  "_diffusers_version": "0.32.2",
+  "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 sha256:826352fb8e5dd13d190cbb679c790f6caf7ed4048c949c00e326cb203e30e56d
+size 485361730