Made Live vs TryOnDiffusion

Made Live enables authors and artists to create, publish, and distribute illustrated books such as children's stories, comics, and graphic novels. It provides tools that support the entire publishing process from initial creation to reaching readers.

This tool stands out by focusing specifically on richly illustrated content, offering features tailored to the unique needs of visual storytelling. Unlike general publishing tools, Made Live emphasizes creative control and accessibility for both beginners and experienced creators.

Made Live combines a user-friendly interface with end-to-end publishing solutions, allowing users to maintain ownership of their work while simplifying distribution. This approach helps creators share their illustrated stories with a broad audience without sacrificing artistic vision.

TryOnDiffusion generates a photorealistic image of how a garment would look on a target person from two inputs: a photo of the person and a photo of someone wearing the garment. The CVPR 2023 research project from University of Washington and Google Research uses a diffusion model with two parallel UNets to preserve fabric detail while warping the clothing across different body poses and shapes. Output runs through 128x128 and 256x256 stages before super-resolution to 1024x1024.

Earlier virtual try-on systems split garment warping and blending into separate steps, which often traded detail for pose flexibility. TryOnDiffusion warps garments implicitly through cross-attention in a Parallel-UNet and fuses warp and blend in one pass. On its test set it reports FID 13.447 and KID 6.964, beating TryOnGAN, SDAFN, and HR-VITON, with 92.72% user preference on random inputs and 95.80% on challenging pose cases.

Fashion researchers, computer vision teams, and e-commerce developers use the project page demo to preview upper-body try-ons interactively. The authors note limitations: upper-body clothing only, reliance on segmentation and pose preprocessing, mostly clean backgrounds in training data, and visualization without fit guarantees.