Using hidden states from a decoder-only LLM as the text conditioning, via a learned adapter, improves text-to-image generation fidelity in the authors' experiments.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Decoder-Only LLMs are Better Controllers for Diffusion Models
Using hidden states from a decoder-only LLM as the text conditioning, via a learned adapter, improves text-to-image generation fidelity in the authors' experiments.