feat(model): Integrate Hunyuan3D Pro api as one of image/text-to-3D backend.

docs/tutorials/image_to_3d.md

@@ -5,14 +5,32 @@ Generate **physically plausible 3D assets** from a single input image, supportin
 ---
 
 ## ⚡ Command-Line Usage
-Support the use of [SAM3D](https://github.com/facebookresearch/sam-3d-objects) or [TRELLIS](https://github.com/microsoft/TRELLIS) as 3D generation model, modify `IMAGE3D_MODEL` in `embodied_gen/scripts/imageto3d.py` to switch model.
+Three 3D generation backends are supported:
+
+- [`SAM3D`](https://github.com/facebookresearch/sam-3d-objects) — local model (default)
+- [`TRELLIS`](https://github.com/microsoft/TRELLIS) — local model
+- `HUNYUAN3D` — Tencent Hunyuan3D Pro cloud API (no local GPU model needed)
+
+Select the backend via `--image3d_model` (case-insensitive). Omit to use the default `SAM3D`.
 
 ```bash
 img3d-cli --image_path apps/assets/example_image/sample_00.jpg \
 apps/assets/example_image/sample_01.jpg \
 --n_retry 2 --output_root outputs/imageto3d
 ```
 
+### Using the Hunyuan3D Cloud Backend
+
+Hunyuan3D Pro runs entirely on Tencent Cloud — useful when you don't have a local GPU. It requires Tencent Cloud Hunyuan3D `SecretId` / `SecretKey` and network access to `ai3d.tencentcloudapi.com` and the COS download host.
+
+```bash
+export TENCENT_SECRET_ID='your-secret-id'
+export TENCENT_SECRET_KEY='your-secret-key'
+img3d-cli --image3d_model HUNYUAN3D \
+  --image_path apps/assets/example_image/sample_00.jpg \
+  --output_root outputs/imageto3d_hunyuan
+```
+
 You will get the following results:
 
 <div class="swiper swiper1" style="max-width: 1000px; margin: 20px auto; border-radius: 12px;">

docs/tutorials/text_to_3d.md

@@ -80,6 +80,27 @@ bash embodied_gen/scripts/textto3d.sh \
 
 > Models with more permissive licenses can be found in `embodied_gen/models/image_comm_model.py`.
 
+### Choosing the 3D Backend
+
+Three 3D generation backends are supported via `--image3d_model` (case-insensitive):
+
+- `SAM3D` (default) — text → image → 3D, local SAM3D model
+- `TRELLIS` — text → image → 3D, local TRELLIS model
+- `HUNYUAN3D` — Tencent Hunyuan3D Pro **text-to-3D** API; skips the text-to-image stage entirely and generates 3D directly from the prompt
+
+### Using the Hunyuan3D Cloud Backend
+
+Hunyuan3D Pro takes the prompt directly to a 3D mesh (no GPU model loaded locally; one job ≈ 3 minutes; Tencent Cloud is billed per submit). Set up credentials once:
+
+```bash
+export TENCENT_SECRET_ID='your-secret-id'
+export TENCENT_SECRET_KEY='your-secret-key'
+text3d-cli --image3d_model HUNYUAN3D \
+  --prompts "small bronze figurine of a lion" \
+  --output_root outputs/textto3d_hunyuan
+```
+
+
 
 The generated results are organized as follows:
 ```sh

embodied_gen/data/backproject_v3.py

@@ -419,7 +419,7 @@ def parse_args():
     parser.add_argument(
         "--save_glb_path", type=str, default=None, help="Save glb path."
     )
-    parser.add_argument("--n_max_faces", type=int, default=30000)
+    parser.add_argument("--n_max_faces", type=int, default=50000)
     args, unknown = parser.parse_known_args()
 
     return args

embodied_gen/data/utils.py

@@ -727,6 +727,7 @@ def save_mesh_with_mtl(
     output_path: str,
     material_base=(250, 250, 250, 255),
     mesh_process: bool = True,
+    glossiness: float = 250.0,
 ) -> trimesh.Trimesh:
     if isinstance(texture, np.ndarray):
         texture = Image.fromarray(texture)
@@ -742,6 +743,8 @@ def save_mesh_with_mtl(
         diffuse=material_base,
         ambient=material_base,
         specular=material_base,
+        # 250 gives a tight visible highlight similar to glossy plastic.
+        glossiness=glossiness,
     )
 
     dir_name = os.path.dirname(output_path)