ElasticDiffusion: Training-Free Arbitrary Size Image Generation Through Global-Local Content Separation

Figure 1. ElasticDiffusion generates high quality images at arbitrary sizes using a pretrained diffusion model trained on a single image size, with equivalent memory footprint and no further training. These results are based on Stable Diffusion1.4, which was trained to generate 512 × 512 images. The examples shown in this collage are presented without any image cropping, stretching, or post-processing.