Grouping related text prompts into a tree and sharing early denoising steps with averaged embeddings saves 50 to 74 percent of diffusion compute on image-embedding-conditioned models while keeping VQA quality essentially equal.
Promptify: Text-to-image generation through interactive prompt exploration with large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Reusing Computation in Text-to-Image Diffusion for Efficient Generation of Image Sets
Grouping related text prompts into a tree and sharing early denoising steps with averaged embeddings saves 50 to 74 percent of diffusion compute on image-embedding-conditioned models while keeping VQA quality essentially equal.