TRELLIS
Scalable and Versatile 3D Generation from images
Generate depth maps from images
Generate 3D models from videos
Complete list of past Spaces of the week
Multimodal Image-to-Video
Expressive Portrait Animation w/ Hierarchical Motion AttentΒ°
Create a video from an image with camera motion
a tiny vision language model
Blind Image Restoration with Instant Generative Reference
Segment body parts in images
a super consistent video depth model
Create images of a given character in different poses
Segment objects in images and videos using text prompts
Easily remove your videos background!
Generate depth estimation map from images
Human parsing model by Meta Reality Labs
Generate 3D models from images
Depth Any Video with Scalable Synthetic Data
Remove/Change background of video.
Detect and mesh faces with depth adjustments