{"ID":3053290,"CreatedAt":"2026-06-04T04:41:36.695875263Z","UpdatedAt":"2026-06-05T23:58:50.513179517Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.04299","arxiv_id":"2606.04299","title":"Efficient and Training-Free Single-Image Diffusion Models","abstract":"We consider the problem of generating images whose internal structure -- defined by the distribution of patches across multiple scales -- matches that of a single reference image. Recent approaches address this problem by training a diffusion model on a single image. But even in this setting, training is computationally expensive and requires hours of optimization. Instead, we model the image using a dataset of its patches at different scales. As this dataset is finite and the dimensionality of its patches is small, the score function for a noisy patch can be computed tractably using an optimal, closed-form denoiser, eliminating the need for neural network training. We integrate this patch-based denoiser into an efficient, training-free image diffusion model, and we describe how our method connects to classical patch-based image restoration techniques. Our approach achieves state-of-the-art generation quality and diversity compared to trained single-image diffusion models, and we demonstrate applications, including unconditional image generation, text-guided stylization, image symmetrization, and retargeting. Further, we show that our approach is compatible with latent space diffusion, and we show multiple additional acceleration techniques to achieve megapixel single-image generation in one second, and gigapixel generation in minutes.","short_abstract":"We consider the problem of generating images whose internal structure -- defined by the distribution of patches across multiple scales -- matches that of a single reference image. Recent approaches address this problem by training a diffusion model on a single image. But even in this setting, training is computationall...","url_abs":"https://arxiv.org/abs/2606.04299","url_pdf":"https://arxiv.org/pdf/2606.04299v1","authors":"[\"Haojun Qiu\",\"Kiriakos N. Kutulakos\",\"David B. Lindell\"]","published":"2026-06-03T00:05:36Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[\"Diffusion Model\"]","has_code":false}