patriotyk/StyleTTS2-LibriTTS
Updated
β’
3
Wan2.1-T2V-14B + Fast 4-step with NAG + Automatic Audio
fast video generation from images & text
Kontext image editing on FLUX[dev]
Audio Conditioned LipSync with Latent Diffusion Models
Duplicate Hugging Face repositories
Create and execute interactive Jupyter notebooks with user input
AI service generating protein structures from user text
Generate person images with new clothes or poses
Stunning images using stable diffusion.
Enhance images using scribbles and prompts
Extend images to desired dimensions using prompts
Prompt with Images in flux[dev]
Generate clickable coordinates on a screenshot