computer vision

Advanced Image Generation: Negative Prompt Optimization and Latent Classifier Guidance

arXiv:2607.14580

summary

The paper introduces a system that automatically creates optimized negative prompts using a fine‑tuned LLM and guides Stable Diffusion with a latent‑space CNN‑RNN classifier to reduce artifacts and improve semantic fidelity of generated images.

Abstract

We present a novel system that integrates negative prompt optimization via a fine-tuned sequence-to-sequence LLM and latent-space classifier guidance to improve the quality of images generated by Stable Diffusion. Our approach automatically generates optimized negative prompts, and employs a CNN-RNN hybrid classifier to evaluate and guide diffusion steps, rolling back low-quality latent updates. Experimental results demonstrate that our dual-guidance framework reduces artifacts and improves semantic fidelity compared to baseline diffusion.

Topics & keywords

#image generation #diffusion models #negative prompting #latent guidance #classifier guidancestable diffusionnegative prompt optimizationlatent-space classifierCNN-RNN hybridsequence-to-sequence LLM