2026
MMFace-DiT: A Dual-Stream Diffusion Transformer for High-Fidelity Multimodal Face Generation
CVPR 2026
Recent multimodal face generation models address the spatial control limitations of text-to-image diffusion models by augmenting text-based conditioning with spatial priors such as segmentation masks, sketches, or edge maps. This multimodal fusion enables controllable synthesis aligned with both hig