Native Hunyuan3D 2.1 Full image-to-mesh extension for Modly, optimized for low-VRAM NVIDIA GPUs with INT8, FP8 and FP16 inference.
Native Modly extension for generating 3D meshes from an image with the full Hunyuan Shape 2.1 model (3.3B) on NVIDIA GPUs with limited VRAM. Author and maintainer: AlefK1708 Version: 0.3.1 Repository: AlefK1708/modly-hunyuan3d-21-lowvram Model: Hunyuan3D Shape 2.1 Full - this is not Mini, Turbo, or Turbo Mini. Backend: native Modly Python integration; no ComfyUI, Gradio, or external server is used. Output: GLB geometry only, with no texture generation.
The Hunyuan Shape 2.1 - Full Low VRAM node accepts an image and returns a mesh output, so it can be connected normally to other compatible nodes in the Modly Workflow.
Main features: Full Hunyuan Shape 2.1 with the complete Safetensors checkpoint. INT8 recommended for GPUs with 8 GB of VRAM, experimental FP8, and FP16. meta initialization, memory-mapped Safetensors loading, and MMGP offloading to reduce RAM peaks. Optional CPU background removal with rembg. Native GLB export without Blender. Attempts to release the heavy pipeline and RAM/VRAM caches after every generation, including errors and cancellations.
The extension returns the geometry produced by Hunyuan Shape without automatic polygon reduction. If you want a lower-poly mesh, connect a dedicated mesh optimization node later in the Modly Workflow.
This version consolidates the geometry-only edition and keeps the repository aligned with the current Modly extension format: Keeps a single image -> mesh node. Keeps manifest.json and generator.py, required by the extension system. Uses setup.py to create the isolated Python environment, following current official Modly extension patterns. Declares Python dependencies in requirements.txt. Removes diagnostic scripts, test files, caches, development artifacts, and Paint/texture components. Removes the previous internal face-count control and leaves mesh optimization to downstream Workflow nodes. Keeps the small memory-cleanup routine directly inside generator.py. Includes only the Tencent Shape 2.1 inference code and configuration required to run the model. Preserves the licenses, redistribution notice, and required credits.
Read the full README on GitHub →