Hunyuan 3D Pro - Text to 3D Model

Generate a textured 3D model from a text prompt with Hunyuan 3D Pro.

Describe an object in plain words, run the workflow, and get back a GLB file, a flat thumbnail render, and an interactive 3D viewer where you can rotate and zoom. The model is ready for game engines, AR pipelines, 3D printing, or downstream Blender work.

No reference image needed. The model handles everything from a text description, so you can prototype objects that don't exist yet.

How do you generate a 3D model from text with Hunyuan 3D Pro?

Type a description of the object in the prompt box, like "a wooden treasure chest with brass fittings" or "a copper gas lamp." Run the workflow. After 30 to 60 seconds you get a GLB file, a thumbnail PNG, and an interactive 3D viewer. Copy the fal.media URL to download the GLB to your computer.

prompt The main input. Describe the object clearly and concretely. Specific physical descriptions work better than abstract concepts: "a copper gas lamp with curved glass shade" gives a sharper result than "vintage lamp." Mention material, era, key features, and color. Avoid scene descriptions (no setting, no background, no lighting). Treat it like describing one object sitting on a turntable.

generate_type Default Normal handles standard mesh generation for most cases. Switch to other modes only if you have a specific reason (high-poly hero asset, low-poly mobile target, etc.).

enable_pbr Off by default for speed. Turn on if you need PBR-textured materials for game engines or AR pipelines. Slower (around 90 seconds vs 30 to 60) but the materials look correct under any lighting setup downstream.

face_count 500,000 polys default. Drop to 100,000 for lightweight web or mobile assets, bump to 1,000,000 for hero shots and detailed display models.

What is text-to-3D good for compared to image-to-3D?

Generating objects from imagination instead of needing a reference photo. Strong when you want to prototype designs that don't exist yet, mock up fantasy or sci-fi props, generate variations of an idea, or skip the step of finding a clean reference image. Image-to-3D is better when you have a specific real object to reproduce.

Game developers use this to mock up inventory items, props, and concept assets directly from design documents. Type "medieval iron-bound oak chest" and you have a starting mesh in a minute instead of waiting on concept art. World-builders generate environmental props and set dressing in bulk. 3D artists use it as a rapid blockout step before refining manually in Blender or ZBrush.

For fantasy and sci-fi work especially, text-to-3D pulls ahead. There's no reference photo for a "cyberpunk neural implant" or "orcish war drum," so the image-to-3D path requires you to first generate a reference image (extra step, extra failure mode). Skipping straight to text-to-3D saves a stage.

Best results come from concrete physical descriptions. The model understands materials (oak, copper, ceramic), eras (Victorian, medieval, retro-futuristic), and structural features (curved, tapered, hollow). It does not understand scenes, lighting, or emotional context, so avoid setting descriptors like "in a forest" or "at sunset."

FAQ

How long does Hunyuan 3D Pro take to generate a model from text? Around 30 to 60 seconds for a standard mesh, depending on face count and complexity. Enabling PBR textures adds another 30 seconds or so. The output appears in the interactive 3D viewer as soon as it's ready, with a fal.media download URL displayed in a text node for grabbing the GLB file.

What prompts work best for Hunyuan 3D Pro text-to-3D? Concrete object descriptions beat abstract concepts. Include material (oak, copper, ceramic), era or style (Victorian, cyberpunk, art deco), key structural features (curved, tapered, hollow), and color when relevant. Keep it to one object on an implied turntable. Skip scene language, lighting words, and emotional descriptors like "epic" or "mystical."

How long do the GLB download URLs last? The fal.media URLs that host the generated GLB expire after a few hours to a day. Download promptly if you want to keep the model permanently. The local file on Floyo's storage (shown in the Local GLB File Path node) sticks around longer and is what downstream workflows in your Floyo account reference.

Can the output be used for 3D printing? Yes, the GLB outputs a watertight mesh suitable for 3D printing. Most slicers want STL or OBJ, so you'll need to convert the GLB through Blender or an online tool. Check the mesh in Blender first for any small geometry artifacts before sending to the slicer, since AI-generated meshes occasionally have non-manifold edges.

Should I use text-to-3D or image-to-3D for Hunyuan 3D Pro? Use image-to-3D when you have a real-world reference photo you want to reproduce in 3D. Use text-to-3D when the object exists only as a description (fantasy, sci-fi, concept design) or when sourcing a clean reference photo would take longer than describing what you want. Both produce the same GLB output format.