ELLA introduces a timestep-aware semantic connector to link LLMs with diffusion models for improved dense prompt following, validated on a new 1K-prompt benchmark.
arXiv preprint arXiv:2311.17946 (2023) 5 ELLA 19
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
ELDiff integrates evidential learning into T2I diffusion via pixel evidence loss and token conflict loss to improve object-wise semantic consistency.
citing papers explorer
-
ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
ELLA introduces a timestep-aware semantic connector to link LLMs with diffusion models for improved dense prompt following, validated on a new 1K-prompt benchmark.
-
ELDiff: When Evidential Learning Meets Text-to-Image Diffusion
ELDiff integrates evidential learning into T2I diffusion via pixel evidence loss and token conflict loss to improve object-wise semantic consistency.