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:2307.10864 (2023) 4
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
AI-T2I improves text-to-image alignment in diffusion models by using aggregation and isolation losses on cross-attention maps to fix scattering and overlap issues.
BindEdit suppresses two forms of attention leakage in diffusion-based editing by binding target tokens to regions, rebalancing cross-attention, and adding a region fidelity term, plus a new multi-object benchmark.
STEDiff improves semantic alignment in text-to-image diffusion models via training-free embedding strengthening with the [EOT] token and a spatial semantic loss, showing gains on T2I-CompBench.
DebFilter mitigates biases in text-to-image diffusion models by applying a fixed offset to the guidance embedding slice in cross-attention during inference.
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.
-
AI-T2I: Aggregating-and-Isolating Cross-Attention to Diffusion Models for Text-to-Image Synthesis
AI-T2I improves text-to-image alignment in diffusion models by using aggregation and isolation losses on cross-attention maps to fix scattering and overlap issues.
-
BindEdit: Taming Attention Leakage for Precise Multi-Object Image Editing
BindEdit suppresses two forms of attention leakage in diffusion-based editing by binding target tokens to regions, rebalancing cross-attention, and adding a region fidelity term, plus a new multi-object benchmark.
-
STEDiff: Strengthening Text Embedding for Text-to-Image Alignment in Diffusion Model
STEDiff improves semantic alignment in text-to-image diffusion models via training-free embedding strengthening with the [EOT] token and a spatial semantic loss, showing gains on T2I-CompBench.
-
DebFilter: Eradicating Biases Stashed in Value
DebFilter mitigates biases in text-to-image diffusion models by applying a fixed offset to the guidance embedding slice in cross-attention during inference.