InnerControl trains lightweight probes on intermediate UNet features to enforce control alignment throughout the denoising trajectory, improving controllability for edges and depth.
ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback: Project Page: liming-ai
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Heeding the Inner Voice: Aligning ControlNet Training via Intermediate Features Feedback
InnerControl trains lightweight probes on intermediate UNet features to enforce control alignment throughout the denoising trajectory, improving controllability for edges and depth.