A two-stage method predicts an intermediate Canny map for structure then renders the image conditioned on appearance and structure, paired with a 100k text-aware dataset, to improve detail preservation in subject-driven generation.
LaMamba-Diff: Linear-time high-fidelity diffusion models based on local at- tention and mamba
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Decomposing Subject-Driven Image Generation via Intermediate Structural Prediction
A two-stage method predicts an intermediate Canny map for structure then renders the image conditioned on appearance and structure, paired with a 100k text-aware dataset, to improve detail preservation in subject-driven generation.