Zonos
Generate high-quality audio from text using various controls
Detect and annotate poses in images and videos
FitDiT is a high-fidelity virtual try-on model.
Find similar images from a dataset
Create 3D models from images
β¨[With v1.0.0] Accelerated TTS on Kokoro-82M
Transform research papers and mathematical concepts into stu
Extract clothing from images using a mask
Audio Conditioned LipSync with Latent Diffusion Models
Gaze detection using Moondream
Generate a high-quality image by expanding and filling a given image
Execute custom code from environment variables
Animation Sketches sequence Colorization
LLM service based on Search and Vector enhanced retrieval
Create top-quality 3D(.GLB) models from text or images
Create a 3D video from images