7
Mask-Adapter-SAM2
🚀
Segment objects in images using text and points
Generate images from text descriptions
Generate videos from images and text prompts
Create a video from an image with camera motion
Generate detailed descriptions from images and videos
a super consistent video depth model
Create 3D models from images
Generate depth maps from images
A Benchmark for Metamorphic Evaluation of T2V Generation
Run the Spaces app on a specified port
Run app using Pixi, install dependencies as needed
Segment Any 3D as Videos
Generate 3D scenes from one or two images