InstructionCrafter generates consistent, step-faithful visual instruction sequences by freezing spatial layers of a video diffusion backbone and adding instruction-aware adapters, improving consistency and per-frame quality over prior methods.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
InstructionCrafter: Generating Consistent and High-Fidelity Visual Instructions
InstructionCrafter generates consistent, step-faithful visual instruction sequences by freezing spatial layers of a video diffusion backbone and adding instruction-aware adapters, improving consistency and per-frame quality over prior methods.