Metraipolis › archive › dc_32cda38ce33d
Efficient Text-to-Image Generation: An Adaptive Step Schedule Controller for Diffusion Models — arXiv:2609.16572
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.16572
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T18:35:06.161Z
- SHA-256 of the archived text
2cc77e75ab030315fb62bd41ccf1b1dfe8224d4aa5bbe7534ef41b6b65ead63a- Stable URL of this page
https://metraipolis.com/documento/dc_32cda38ce33d
How to cite
Efficient Text-to-Image Generation: An Adaptive Step Schedule Controller for Diffusion Models — arXiv:2609.16572 — arXiv (en), https://arxiv.org/abs/2609.16572 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_32cda38ce33d (Metraipolis archive dc_32cda38ce33d, sha256 2cc77e75ab030315fb62bd41ccf1b1dfe8224d4aa5bbe7534ef41b6b65ead63a)
BibTeX
@misc{dc32cda38ce33d,
title = {Efficient Text-to-Image Generation: An Adaptive Step Schedule Controller for Diffusion Models — arXiv:2609.16572},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.16572},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_32cda38ce33d; sha256 2cc77e75ab030315fb62bd41ccf1b1dfe8224d4aa5bbe7534ef41b6b65ead63a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16572. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.16572 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T18:03:09.665Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).