Initial release

.gitattributes

@@ -0,0 +1,36 @@
+*.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
+*.tar.gz filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,45 @@
+---
+license: mit
+pipeline_tag: image-to-3d
+tags:
+- triposg
+- 3d-generation
+- rectified-flow
+---
+# TripoSG - High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models
+
+TripoSG is a state-of-the-art image-to-3D generation foundation model that leverages large-scale rectified flow transformers to produce high-fidelity 3D shapes from single images.
+
+## Model Description
+
+### Model Architecture
+
+TripoSG utilizes a novel architecture combining:
+- Rectified Flow (RF) based Transformer for stable, linear trajectory modeling
+- Advanced VAE with SDF-based representation and hybrid geometric supervision
+- Cross-attention mechanism for image feature condition
+- 1.5B parameters operating on 2048 latent tokens
+
+## Intended Uses
+
+This model is designed for:
+- Converting single images to high-quality 3D meshes
+- Creative and design applications
+- Gaming and VFX asset creation
+- Prototyping and visualization
+
+## Requirements
+
+- CUDA-capable GPU (>8GB VRAM)
+
+## Usage
+
+For detailed usage instructions, please visit our [GitHub repository](https://github.com/VAST-AI-Research/TripoSG).
+
+## About
+
+TripoSG is developed by [Tripo](https://www.tripo3d.ai), [VAST AI Research](https://github.com/orgs/VAST-AI-Research), pushing the boundaries of 3D Generative AI.
+For more information:
+- [GitHub Repository](https://github.com/VAST-AI-Research/TripoSG)
+- [Paper](https://arxiv.org/abs/2502.06608)
+- [Gradio Demo](https://huggingface.co/spaces/VAST-AI/TripoSG)

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 @@
+{
+  "_name_or_path": "facebook/dinov2-large",
+  "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": "4.45.2",
+  "use_swiglu_ffn": false
+}

image_encoder_dinov2/model.safetensors

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

model_index.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "TripoSGPipeline",
+  "_diffusers_version": "0.30.3",
+  "feature_extractor_dinov2": [
+    "transformers",
+    "BitImageProcessor"
+  ],
+  "image_encoder_dinov2": [
+    "transformers",
+    "Dinov2Model"
+  ],
+  "scheduler": [
+    "triposg.schedulers.scheduling_rectified_flow",
+    "RectifiedFlowScheduler"
+  ],
+  "transformer": [
+    "triposg.models.transformers.triposg_transformer",
+    "TripoSGDiTModel"
+  ],
+  "vae": [
+    "triposg.models.autoencoders.autoencoder_kl_triposg",
+    "TripoSGVAEModel"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,7 @@
+{
+  "_class_name": "RectifiedFlowScheduler",
+  "_diffusers_version": "0.30.3",
+  "num_train_timesteps": 1000,
+  "shift": 1,
+  "use_dynamic_shifting": false
+}

transformer/config.json

@@ -0,0 +1,9 @@
+{
+  "_class_name": "TripoSGDiTModel",
+  "_diffusers_version": "0.30.3",
+  "cross_attention_dim": 1024,
+  "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 sha256:9192b5923f7b605b394192809aa2ceb73bf0f4009674d8e3b999b45bb97d4bf2
+size 5758280104

vae/config.json

@@ -0,0 +1,14 @@
+{
+  "_class_name": "Tripo2VAEModel",
+  "_diffusers_version": "0.30.3",
+  "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:a2e667c24927a5a35e5f19fcb4c75890e9399aa966b6db8131d7df733a750c8b
+size 970685468