One line. Many voicesSeek and you shall find

genception.github.io faviconVideo Generation Models are General-Purpose Vision Learners

kept by

GenCeption turns a pretrained video generation diffusion model into a unified, feed‑forward vision system that matches or beats task‑specific SOTA across depth, normals, pose, segmentation and keypoints using text prompts.

read later

For all the tabs you promised to read.
Save to read. Read to clear.

Close tabs. Keep links.