An Efficient Test-Time Scaling Approach for Image Generation

Abstract: Image generation has emerged as a mainstream application of large generative AI models. Just as test-time compute and reasoning have helped LLMs improve their capabilities, similar benefits have also been observed with image generation models. In particular, searching over noise samples for diffusion and flow models has shown to scale well with test-time compute. While recent works have explored allocating non-uniform inference-compute budgets across different denoising steps, they rely on greedy algorithms and allocate the compute budget ineffectively. In this work, we study this problem and propose solutions to fix it. We propose the Verifier-Threshold method which automatically reallocates test-time compute and delivers substantial efficiency improvements. For the same performance on the GenEval benchmark, we achieve a 2-4x reduction in computational time over the state-of-the-art method.