122
MeshLRM (Unofficial)
ðŊ
Create 3D meshes from images
Apply the motion of a video on a portrait
Interact with Florence-2 to analyze images and generate descriptions
Enhance and upscale images with controlnet guidance
Generate personalized images with a face preservation
Video captioning/tracking
Generate images from prompts using powerful LORA models
Generate instruction-response pairs from text
Generate detailed captions for images