397
LatentSync
π
Audio Conditioned LipSync with Latent Diffusion Models
Generate detailed script for podcast or lecture from text input
Run image generation web UI
Generate images from text prompts with a specific style
Generate customized portraits using ID images and prompts
Train Free PersonalizΒ° Diff w/ Stochastic Optimal Control
With Neg Prmpt, W/H, Steps, CFG, Seed, & Method. No GPU Req.
With IP Adapter