We present two models, SDXS-512 and SDXS-1024, achieving inference speeds of approximately 100 FPS (30x faster than SD v1.5) and 30 FPS (60x faster than SDXL) on a single GPU. Assuming the image ...
This work presents Depth Anything, a highly practical solution for robust monocular depth estimation by training on a combination of 1.5M labeled images and 62M+ unlabeled images.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback