Files
Depth-Anything/controlnet
2024-01-22 09:14:27 +08:00
..
2024-01-22 09:14:27 +08:00
2024-01-22 09:14:27 +08:00

Depth-Conditioned ControlNet based on Depth Anything

We use Diffusers to re-train a better depth-conditioned ControlNet based on our Depth Anything.

Please download our config file and pre-trained weights, then follow the instructions in Diffusers for inference.

Depth-to-Image Synthesis

demo2 demo1

Video Editing

The demos below are generated by MagicEdit. The middle video is generated by MiDaS-based ControlNet, while the last video is generated by Depth Anything-based ControlNet.