paper-with-me

Papers

Efficient Text-to-Image Generation: An Adaptive Step Schedule Controller for Diffusion Models

2026-09-15 · Kuluhan Binici, Cihan Acar, Shivam Aggarwal, Siying Liu, Tulika Mitra arxiv

Text-to-image diffusion models often use a fixed number of denoising steps, balancing time costs and image quality. However, the optimal number of steps depends on the complexity of the input text prompt. We propose an adaptive diffusion controller that dynamically adjusts the number of steps to generate high-quality images efficiently, without additional model training. By leveraging a mixture of step schedules with varying step sizes and evaluating the error term discrepancy at each timestep, our method transitions between schedules to optimize performance. Experiments on COCO and DiffusionDB show that our approach reduces inference time while maintaining visual fidelity, offering a more efficient alternative for text-to-image diffusion models.

📄 PDF Abstract BibTeX arXiv:2609.16572

Code (0)

등록된 구현이 없습니다.

Tasks

Text-to-Image Generation

Similar Papers 제목 키워드 기반

SeqDiffuSeq: Text Diffusion with Encoder-Decoder Transformers

2022-12-20 · Hongyi Yuan, Zheng Yuan, Chuanqi Tan, Fei Huang 외

Diffusion model, a new generative modelling paradigm, has achieved great success in image, audio, and video generation. However, considering the discrete categorical nature of text, it is not trivial to extend continuous…

DecoderDenoisingText GenerationVideo Generation

Schedule On the Fly: Diffusion Time Prediction for Faster and Better Image Generation

2024-12-02 · CVPR 2025 1 · Zilyu Ye, Zhiyang Chen, Tiancheng Li, Zemin Huang 외

Diffusion and flow models have achieved remarkable successes in various applications such as text-to-image generation. However, these models typically rely on the same predetermined denoising schedules during inference f…

DenoisingImage GenerationText to Image GenerationText-to-Image Generation

Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation

2026-04-21 · Johannes Schusterbauer, Ming Gui, Yusong Li, Pingchuan Ma 외 arxiv

Diffusion- and flow-based models usually allocate compute uniformly across space, updating all patches with the same timestep and number of function evaluations. While convenient, this ignores the heterogeneity of natura…

Image Generation

Adaptively Controllable Diffusion Model for Efficient Conditional Image Generation

2024-11-19 · Yucheng Xing, Xiaodong Liu, Xin Wang

With the development of artificial intelligence, more and more attention has been put onto generative models, which represent the creativity, a very important aspect of intelligence. In recent years, diffusion models hav…

Conditional Image GenerationImage Generation

Optimal Stepsize for Diffusion Sampling

2025-03-27 · Jianning Pei, Han Hu, Shuyang Gu

Diffusion models achieve remarkable generation quality but suffer from computational intensive sampling due to suboptimal step discretization. While existing works focus on optimizing denoising directions, we address the…

DenoisingImage GenerationText to Image GenerationText-to-Image Generation