Overview

The Text to SimReady workflow allows you to generate a simulation-ready 3D asset starting from a text description alone. The system uses Gemini to generate reference images from your prompt, then processes them through the same mesh generation and texturing pipeline as Image to SimReady.

Step 1: Asset Name

The Asset Name is the label used to keep your project files organized. It becomes the base name for the generated output files.

Step 2: Generation Prompt

The Generation Prompt is the most important input in this workflow. It is used twice in the pipeline:

• First, Gemini uses it to generate three candidate reference images of the object.
• Later, the selected image together with the prompt is used to generate the 3D mesh.

<aside> 💡 Best Practices for Prompts

</aside>

• Be descriptive: specify object type, material, shape, and context. Example: "ripe yellow banana on a white background, slightly curved, smooth waxy skin".
• Avoid ambiguity: short one-word prompts ("banana") may work, but multi-attribute prompts yield higher-quality meshes and better physical property estimation.
• Include physical characteristics: prompts that describe physical properties (wooden, metallic, rubbery, rigid, flexible) help the pipeline assign accurate simulation properties.
• Describe geometry: include shape details like angular, spherical, flat, multi-part assemblies, or objects with openings/joints.

Gemini will generate three candidate images. Each preview can be refreshed if the results are unsatisfactory. Select the best one before proceeding to mesh generation.

Step 3: Mesh Generation

Once a candidate image is selected, mesh generation runs the same pipeline as Image to SimReady:

• High quality: uses Tencent Hunyuan3D v3.0/v3.1 for detailed geometry.