Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion
By: Zheqi Lv , Junhao Chen , Qi Tian and more
Potential Business Impact:
Fixes AI art mistakes while it's being made.
Diffusion models have become the mainstream architecture for text-to-image generation, achieving remarkable progress in visual quality and prompt controllability. However, current inference pipelines generally lack interpretable semantic supervision and correction mechanisms throughout the denoising process. Most existing approaches rely solely on post-hoc scoring of the final image, prompt filtering, or heuristic resampling strategies-making them ineffective in providing actionable guidance for correcting the generative trajectory. As a result, models often suffer from object confusion, spatial errors, inaccurate counts, and missing semantic elements, severely compromising prompt-image alignment and image quality. To tackle these challenges, we propose MLLM Semantic-Corrected Ping-Pong-Ahead Diffusion (PPAD), a novel framework that, for the first time, introduces a Multimodal Large Language Model (MLLM) as a semantic observer during inference. PPAD performs real-time analysis on intermediate generations, identifies latent semantic inconsistencies, and translates feedback into controllable signals that actively guide the remaining denoising steps. The framework supports both inference-only and training-enhanced settings, and performs semantic correction at only extremely few diffusion steps, offering strong generality and scalability. Extensive experiments demonstrate PPAD's significant improvements.
Similar Papers
Adaptive Guidance Semantically Enhanced via Multimodal LLM for Edge-Cloud Object Detection
CV and Pattern Recognition
Helps cameras see better in dark or crowded places.
MIND-Edit: MLLM Insight-Driven Editing via Language-Vision Projection
CV and Pattern Recognition
Makes AI understand pictures better for editing.
Weak Supervision Dynamic KL-Weighted Diffusion Models Guided by Large Language Models
Computation and Language
Makes computer pictures match words better.