- Added intelligent quality checkers and auto-retry pipeline for `image-to-3d` and `text-to-3d`. - Added unit tests for quality checkers. - `text-to-3d` now supports more `text-to-image` models, pipeline success rate improved to 94%.
Improve the scale restoration logic to make it more robust.
Adapt to huggingface space.
Add EmbodiedGen version v0.1.0.
