A 20M-parameter adapter trained only on English image-text pairs adapts frozen diffusion models to generate images from prompts in over 110 languages, using a multilingual image-text encoder as its text encoder.
Cross-lingual and multilingual clip
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MuLan: Adapting Multilingual Diffusion Models for Hundreds of Languages with Negligible Cost
A 20M-parameter adapter trained only on English image-text pairs adapts frozen diffusion models to generate images from prompts in over 110 languages, using a multilingual image-text encoder as its text encoder.