Skip to main content

How to use the Text to 3D feature?

Updated over a month ago

Meshy Text to 3D allows you to generate highly detailed 3D objects simply by describing them in natural language. Whether it’s a product idea, creature concept, Game asset prop, or something totally imaginative, just type your prompt and let Meshy bring it to life in 3D - no modeling experience required!

  1. Go to workspace at https://www.meshy.ai/workspace.

  2. Click "New Model", and switch to "Text to 3D".

  3. Enter a detailed description of your model. Be specific—describe objects, shapes, styles, and unique characteristics to guide our AI.

    Model Generation - Text to 3D

  4. Click "Generate" and wait for a few seconds for it to generate 4 draft models.

  5. Select one and click "Continue".

  6. Your model will be available for download and texture now.

✍️ Text to 3D Tips

  • Start simple. Example: “A werewolf character” before adding additional detail e.g. “with sharp claws, glowing eyes, wearing leather armor and standing in T-Pose.”

  • Focus on describing a single object, not a full scene.

  • Focus on describing about three to six key descriptive details. Too many might dilute or confuse the final output.

  • Be specific: type “shiny gold metal” instead of “looks beautiful.”

  • Use reference terms: “Like motocross gear,” “in the style of an ancient artifact.”

  • Add pose terms like “T-Pose” to get a result ready for humanoid character rigging.

  • Use Meshy Prompt Tools to extract text from images or add style tags.

Examples of strong prompts:

  • “A sleek, retro-futuristic android head with a glowing eye”

  • "Humanoid Male wearing a motorcycle helmet and biker outfit, with faded denim jeans, T-Pose"

  • “A geometric sculpture of cubes and spheres, smooth and polished”

Avoid:

  • Complex or contradictory descriptions

  • Prompts that might attempt to create non-physical details in your generation, e.g. smoke, glitter, electric magic energy

  • Very abstract concepts without tangible visual references

  • Prompts focused on fine details like individual strands of hair

  • Excessive use of adjectives that might dilute the core concept

  • Technical jargon that the model might not understand correctly

For further assistance with prompt engineering and ideas, feel free to join the Meshy Discord Community and ask!

Did this answer your question?