Diffusion Probe: Generated Image Result Prediction Using CNN Probes

ArXi:2602.23783v3 Announce Type: replace Text-to-image (T2I) diffusion models lack an efficient mechanism for early quality assessment, leading to costly trial-and-error in multi-generation scenarios such as prompt iteration, agent-based generation, and flow-grpo. We reveal a strong correlation between early diffusion cross-attention distributions and final image quality. Based on this finding, we