An experimental version of IP-Adapter-FaceID: we use face ID embedding from a face recognition model instead of CLIP image embedding, additionally, we use LoRA to improve ID consistency. IP-Adapter-FaceID can generate various style images conditioned on a face with only text prompts.
Related Model
img2img + pix2pix – realv30
img2img + pix2pix - realv30
Date a live 园神凛祢 そのがみ りんね Sonogami Rinne
Date a live 园神凛祢 そのがみ りんね Sonogami Rinne
blue_pencil_realistic
blue_pencil_realistic
AsagaoMix
AsagaoMix
Earth Animix XL
Earth Animix XL
Endjourney
Endjourney
No comments...