Performance Plateaus in Inference-Time Scaling for Text-to-Image Diffusion Without External Models

• URL: http://arxiv.org/abs/2506.12633v1
• Date: Sat, 14 Jun 2025 21:25:08 GMT
• Title: Performance Plateaus in Inference-Time Scaling for Text-to-Image Diffusion Without External Models
• Authors: Changhyun Choi, Sungha Kim, H. Jin Kim,
• Abstract summary: We apply Best-of-N inference-time scaling to algorithms that optimize the initial noise of a text-to-image diffusion model.<n>We demonstrate that inference-time scaling for text-to-image diffusion models in this setting quickly reaches a performance plateau.
• Score: 31.873727540047156
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, it has been shown that investing computing resources in searching for good initial noise for a text-to-image diffusion model helps improve performance. However, previous studies required external models to evaluate the resulting images, which is impossible on GPUs with small VRAM. For these reasons, we apply Best-of-N inference-time scaling to algorithms that optimize the initial noise of a diffusion model without external models across multiple datasets and backbones. We demonstrate that inference-time scaling for text-to-image diffusion models in this setting quickly reaches a performance plateau, and a relatively small number of optimization steps suffices to achieve the maximum achievable performance with each algorithm.

Related papers

• Fast constrained sampling in pre-trained diffusion models [77.21486516041391]
  We propose an algorithm that enables fast and high-quality generation under arbitrary constraints.<n>During inference, we can interchange between gradient updates computed on the noisy image and updates computed on the final, clean image.<n>Our approach produces results that rival or surpass the state-of-the-art training-free inference approaches.
  arXiv  Detail & Related papers  (2024-10-24T14:52:38Z)
• OrientDream: Streamlining Text-to-3D Generation with Explicit Orientation Control [66.03885917320189]
  OrientDream is a camera orientation conditioned framework for efficient and multi-view consistent 3D generation from textual prompts. Our strategy emphasizes the implementation of an explicit camera orientation conditioned feature in the pre-training of a 2D text-to-image diffusion module. Our experiments reveal that our method not only produces high-quality NeRF models with consistent multi-view properties but also achieves an optimization speed significantly greater than existing methods.
  arXiv  Detail & Related papers  (2024-06-14T13:16:18Z)
• Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction [31.503662384666274]
  In science and engineering, the goal is to infer an unknown image from a small number of measurements collected from a known forward model describing certain imaging modality. Motivated Score-based diffusion models, due to its empirical success, have emerged as an impressive candidate of an exemplary prior in image reconstruction.
  arXiv  Detail & Related papers  (2024-03-25T15:58:26Z)
• AdaDiff: Adaptive Step Selection for Fast Diffusion Models [82.78899138400435]
  We introduce AdaDiff, a lightweight framework designed to learn instance-specific step usage policies.<n>AdaDiff is optimized using a policy method to maximize a carefully designed reward function.<n>We conduct experiments on three image generation and two video generation benchmarks and demonstrate that our approach achieves similar visual quality compared to the baseline.
  arXiv  Detail & Related papers  (2023-11-24T11:20:38Z)
• AdaDiff: Accelerating Diffusion Models through Step-Wise Adaptive Computation [32.74923906921339]
  Diffusion models achieve great success in generating diverse and high-fidelity images, yet their widespread application is hampered by their inherently slow generation speed. We propose AdaDiff, an adaptive framework that dynamically allocates computation resources in each sampling step to improve the generation efficiency of diffusion models.
  arXiv  Detail & Related papers  (2023-09-29T09:10:04Z)
• AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration [57.846038404893626]
  We propose to search the optimal time steps sequence and compressed model architecture in a unified framework to achieve effective image generation for diffusion models without any further training. Experimental results show that our method achieves excellent performance by using only a few time steps, e.g. 17.86 FID score on ImageNet 64 $times$ 64 with only four steps, compared to 138.66 with DDIM.
  arXiv  Detail & Related papers  (2023-09-19T08:57:24Z)
• ExposureDiffusion: Learning to Expose for Low-light Image Enhancement [87.08496758469835]
  This work addresses the issue by seamlessly integrating a diffusion model with a physics-based exposure model. Our method obtains significantly improved performance and reduced inference time compared with vanilla diffusion models. The proposed framework can work with both real-paired datasets, SOTA noise models, and different backbone networks.
  arXiv  Detail & Related papers  (2023-07-15T04:48:35Z)
• ACDMSR: Accelerated Conditional Diffusion Models for Single Image Super-Resolution [84.73658185158222]
  We propose a diffusion model-based super-resolution method called ACDMSR. Our method adapts the standard diffusion model to perform super-resolution through a deterministic iterative denoising process. Our approach generates more visually realistic counterparts for low-resolution images, emphasizing its effectiveness in practical scenarios.
  arXiv  Detail & Related papers  (2023-07-03T06:49:04Z)
• Variational Diffusion Models [33.0719137062396]
  We introduce a family of diffusion-based generative models that obtain state-of-the-art likelihoods on image density estimation benchmarks. We show that the variational lower bound (VLB) simplifies to a remarkably short expression in terms of the signal-to-noise ratio of the diffused data.
  arXiv  Detail & Related papers  (2021-07-01T17:43:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.