Hunyuan3D generates textured 3D assets from reference images or text and can run on your own computer. It's for 3D artists, hobbyists and developers who want AI-generated meshes they can use in other software. It supports macOS, Windows and Linux; Hunyuan3D Studio is a separate hosted option.
Shape and texture generation are separate. Hunyuan3D-DiT creates geometry from an image, while Hunyuan3D-Paint adds texture maps. That separation lets you generate a bare mesh or apply textures to a model you've made yourself, without generating its shape again. Multiview models accept several reference images for shape generation, and smaller models and distilled Fast and Turbo variants provide alternatives to the standard models.
For artists, the Blender addon brings generation into an existing modeling workflow through a locally hosted API. Community integrations include ComfyUI-Hunyuan3DWrapper and ComfyUI-3D-Pack. Meshes can export as GLB or OBJ for use elsewhere.
You can use a self-hosted Gradio browser interface or connect your own application to the local API for image-to-3D, text-to-3D and mesh texturing. The Python library also exposes shape and texture generation separately. Local generation runs on your hardware; the official website offers generation without self-hosting. The stated GPU memory requirement is 6 GB of VRAM for shape generation, or 16 GB for shape and texture generation together. The linked Hunyuan3D 2.0 release uses Tencent’s custom community license, which excludes the European Union, United Kingdom and South Korea from its territory. Check the exact release’s terms, including commercial conditions.
Claim this page and we'll verify you by hand. Hunyuan3D gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Hunyuan3D?Promote it
Something wrong or outdated on this page?
135.6KUpdated 49 minutes agoGPL-3.0
macOS · Windows · Linux · Web#ControlNet#Inpainting#LoRA
ComfyUI is a local visual AI workspace for artists and technical teams who want to control how images, video, audio, 3D models and text are made. Its node canvas shows each model and processing step, so users can build and adjust workflows without writing code. It runs on your hardware.
1.8KUpdated 2 years ago
macOS · Windows · Linux#Batch processing#Hugging Face integration
Stable Fast 3D turns a single object image into a textured 3D mesh on your own hardware. It's aimed at game and VR developers, designers and people creating product models for e-commerce. Built on TripoSR, it uses a retrained model designed to produce meshes and textures suitable for use in games and other 3D projects.
34.4KUpdated 2 months agoApache-2.0
macOS · Windows · Linux · Docker · Web#Batch processing#Human approval#MCP
13.7KUpdated 11 months agoMIT
Linux · Web#Hugging Face integration#Multimodal input
4.5KUpdated 2 years agoApache-2.0
Docker · Web#Image-to-image
InstantMesh generates a 3D mesh from a single image on your own machine. It's for creators exploring image-based 3D assets and researchers working on 3D reconstruction. The Python project is open source under Apache 2.0 and uses PyTorch with CUDA for GPU processing.
7KUpdated 4 months agoMIT
#Batch processing
TripoSR reconstructs a 3D object from a single image on your own hardware. Developed by Tripo AI and Stability AI, it's an open-source model for researchers, developers, and artists who want image-based 3D generation they can use in their own projects. The MIT license covers both the source code and pretrained models.
ChatDev is a self-hosted platform for building teams of AI agents through a visual workflow editor. It's for people who want agents to collaborate on research, data analysis or software projects without writing the orchestration code themselves. You define each agent's role and how information passes between them.
TRELLIS is a local AI model for generating 3D assets from images or text prompts, aimed at 3D artists and researchers exploring asset creation. It can produce meshes, radiance fields and 3D Gaussians from the same underlying representation, so you can choose an output suited to your rendering or editing work.