Advanced Image Generation: Negative Prompt Optimization and Latent Classifier Guidance
On the map: Diffusion models → Diffusion foundations and sampling
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 4 of its 4 references that are in the map. First posted on arXiv 16 Jul 2026.
Builds on
4 of 4 references.
References · 4
- 2024InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimizationcited by 123
- 2024Controllable Generation with Text-to-Image Diffusion Models: A Surveycited by 82
- 2024Optimizing Negative Prompts for Enhanced Aesthetics and Fidelity in Text-To-Image Generationcited by 5
- 2025Fine-Grained Alignment and Noise Refinement for Compositional Text-to-Image Generationcited by 4
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2023End-to-End Diffusion Latent Optimization Improves Classifier Guidance
- 2025Dynamic VLM-Guided Negative Prompting for Diffusion Models
- 2022Meta-Learning via Classifier(-free) Diffusion Guidance
- 2024Dynamic Negative Guidance of Diffusion Models
- 2024Improving image synthesis with diffusion-negative sampling
- 2025Diffusion Models with Adaptive Negative Sampling Without External Resources
- 2025Boosting Generative Image Modeling via Joint Image-Feature Synthesis
- 2022Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidance