Multi Language Prompt Understanding With Frozen Text Encoder

via “text embedding integration with dual-encoder architecture”

text-to-image model by undefined. 6,84,555 downloads.

Unique: Uses frozen pre-trained text encoders rather than training custom encoders, enabling leverage of large-scale text understanding from CLIP/T5 training; implements cross-attention fusion allowing flexible prompt length and semantic richness

vs others: More semantically rich than token-based conditioning because embeddings capture meaning; more efficient than end-to-end training because text encoder is frozen; more flexible than fixed-vocabulary approaches