The Three AI Models Behind Every File Here
No model picker, no routing layer, no vendor being resold: three named models do all the work, they run on our own hardware, and this page says exactly which does what.
The three models we run
That is the complete list. There is no fourth model behind the button and no vendor being resold.
Hunyuan3D-2
The mesh engine. Turns one image into a textured 3D model and bakes the texture on.
Read the specz-image-turbo
Draws the concept image from your text prompt in about six seconds, so text to 3D has something to build from.
Read the specflux.2
Optional concept edits — change the pose, the angle or the material before you commit the picture to the 3D engine.
Read the specThe three engines, side by side
These we can describe exactly, because we deploy them. Every figure below is what this deployment produces, not a headline number from a paper.
| Model | Job on this site | Input | Output | Rough time |
|---|---|---|---|---|
| Hunyuan3D-2 | Builds the mesh and bakes the texture | One image | .glb, roughly 40k–120k triangles | ~80s |
| z-image-turbo | Draws the concept image for text to 3D | Your text prompt | One concept image | ~6s |
| flux.2 | Optional edits to the concept before meshing | Image plus an instruction | Revised concept image | Varies |
Text to 3D runs the first two in sequence, which is where the familiar ninety-second figure comes from. Image to 3D skips straight to the mesh engine and finishes sooner.
From your prompt to a finished file
Four stages. The middle two are the only ones that touch a GPU, and you approve the hand-over between them.
Text to 3D or image to 3D
Type a sentence, or drop a photo. Image to 3D skips straight to the mesh stage; text to 3D needs a picture first.
Concept image
z-image-turbo draws your prompt in about six seconds. You keep it, redraw it, or edit it with flux.2.
Mesh and texture
Hunyuan3D-2 turns that one image into geometry and bakes the texture onto it. This is the slow step, and the progress you see is real job state rather than an animation.
Download the .glb
Take the file. Convert it to STL, OBJ or USDZ in your browser if the next tool needs something else.
Why name them at all? Because a named model is reproducible and a product name is not. If you like what you got today, you can get the same behaviour next month — and you can go and read what the model does rather than taking our word for it. The comparison page makes the same argument at more length.
Make a 3D model right here
You do not have to go back to the home page. Type a prompt or drop an image, and take the .glb — free, anonymous, no watermark.
Run all three in ninety seconds
One prompt puts the whole pipeline to work. Free, anonymous, no watermark on anything that comes out.
FreeNo signupNo watermarkDownloads as .glb