New controllable generation framework uses Mamba-2 diffusion backbones, suggesting improved image and video outputs.
We propose SSD-Control, the first ControlNet-style controllable generation framework for Mamba-2 diffusion backbones. Our approach introduces Zero-Projection SSD Adapters and Condition-Injected State Modulation to enable depth, pose, and edge-conditioned image and video generation while preserving O(LN) linear complexity.
No takes yet. Share an insight, caveat, or question.
Hiroki Abe (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: