I know nothing about 3D. The AI built my character into a talking 3D model in five days.
He wanted his AI character AYN to move and talk like a VTuber. The AI drew the art, Tripo made the 3D shapes, and the AI drove Blender by script to build, fix and export the model, while he only looked at the renders and said what looked wrong. The finished model has 16 expressions and lip sync that follows the expression.
How it works
- The AI drew the face and full body art from ten reference images he gave it, Tripo turned the art into 3D shapes, using grey shaded art for shape and coloured art for colour, the AI ran Blender headless by script to assemble, fix and export the model, showing him renders to judge, After six failed rebuilds in parts, they restarted from the face art and finished the model over five days
Why it’s worth knowing
A man who cannot use Blender ended up with a jointed, talking 3D character, because the agent ran the software and he only had to judge the pictures.
Where it’s from
Summarized from a public post on note.com. See the original ↗