GreenStableYolo: Optimizing Inference Time and Image Quality of Text-to-Image Generation

Jingzhi Gong, Sisi Li, Giordano d'Aloisio, Zishuo Ding, Yulong Ye +2 more
7/20/2024
cs.CVcs.AI

No confident code implementation found for this paper.

Abstract

Tuning the parameters and prompts for improving AI-based text-to-image generation has remained a substantial yet unaddressed challenge. Hence we introduce GreenStableYolo, which improves the parameters and prompts for Stable Diffusion to both reduce GPU inference time and increase image generation quality using NSGA-II and Yolo. Our experiments show that despite a relatively slight trade-off (18%) in image quality compared to StableYolo (which only considers image quality), GreenStableYolo achieves a substantial reduction in inference time (266% less) and a 526% higher hypervolume, thereby advancing the state-of-the-art for text-to-image generation.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection

88% match1 repo562025

KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis

87% match1 repo1472026

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer

87% match1 repo8.6k2025

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer

87% match2026

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

86% match1 repo1.9k2026

DiT-Air: Revisiting the Efficiency of Diffusion Model Architecture Design in Text to Image Generation

86% match2025

Cite this paper

@article{gong2024greenstableyolo,
  title  = {GreenStableYolo: Optimizing Inference Time and Image Quality of Text-to-Image Generation},
  author = {Jingzhi Gong and Sisi Li and Giordano d'Aloisio and Zishuo Ding and Yulong Ye and William B. Langdon and Federica Sarro},
  year   = {2024},
  eprint = {2407.14982},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2407.14982v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2407.14982.svg)](https://codeofpaper.com/paper/2407.14982)

Discussion