SpaceFlow Adds Per-Region Geometric and Appearance Control to 3D Generation
Summary
SpaceFlow lets 3D asset generation apply different geometric-conditioning strengths and distinct text or image prompts per region, so some parts stay faithful to input geometry while others rely on generative priors. In pairwise user studies it wins 71% of trials vs SpaceControl τ=3 and 78% vs τ=10 for overall preference, and beats TRELLIS 65%/67% on prompt faithfulness and overall across 337 trials with 29 raters.
Originally reported by huggingface.co
Read the original article →Original headline: SpaceFlow Adds Per-Region Geometric and Appearance Control to 3D Generation