<aside> 💡

Most 3D generation models support text to 3D and image to 3D in the meantime. Since image to 3D is more controllable, we will use text to 3D as example today, but you are free to test with text to 3D generation.

</aside>

1. AI generation of 3D models with opensource programs

1.1 Trellis

🌟 Features

• High Quality: It produces diverse 3D assets at high quality with intricate shape and texture details.
• Versatility: It takes image (or text, coming soon) prompts and can generate various final 3D representations including but not limited to Radiance Fields, 3D Gaussians, and meshes, accommodating diverse downstream requirements.
• Flexible Editing: It allows for easy editings of generated 3D assets, such as generating variants of the same object or local editing of the 3D asset.

• Start with ➡️： Online Demo (Demo for testing purpose, free but may become unavailable)

Bellow are the input image example and the video and 3D (glb mesh or gaussian point cloud) output.

sample.glb

sample (2).mp4

<aside> 💡

It is possible to install Trellis inside comfyui and connect with your workflow form https://github.com/if-ai/ComfyUI-IF_Trellis, but it require at lest 8G GPU RAM, and it is very complicate to install.

</aside>

1.2 Hunyuan3D 2.0

Better quality (shaper) compare with Trellis but require longer computation time. Text to 3D mode is available now.