Lore

Garbage 3D product mannequin

# Garbage 3D product mannequin

Turn a single product image into a crude, textured 3D model and use it only as a mannequin: it fixes the product's pose, camera angle and position, and contributes nothing to realism. The model will look terrible, and that is acceptable. The principle is in Split placement from appearance: a stand-in sets geometry, the image model sets looks.

Procedure (Weavy)

  1. Plug the product image into a 3D node. Rodin v2 or Meshy both work. Any generator that returns a texture is fine, because the texture is what lets you see which part of the label is facing the camera.
  2. In the 3D viewer, rotate the model, orbit the camera and position it until the part of the label or the angle you want is showing.
  3. Export that view. It becomes reference image A, see compositor-annotation-layers for labelling it and master-prompt-with-reference-image-roles for how the image model reads it.
  4. The final image model (Nano Banana) renders the realistic result from separate appearance references.

What it gets you

Known limits

Related

Texture requirement

Texture requirement

The mannequin's geometry quality and appearance do not matter, but the 3D asset must carry some texture, even a bad one. Without a texture the image model estimates the product's position in space poorly, and placement drifts.

Aspect-ratio mismatch with the output

The layout image can be 1:1 while the output is 9:16. In that case the model has to guess the product's size and fill the extra pixels above and below. In the author's run the rotation still came out in line with the mannequin. Expect size and framing to be approximate, and expect rotation and pose to be reliable.