PuLID Lightning

Faster version of PuLID, a novel tuning-free face customization method for text-to-image generation

~210.80s
~$0.217

This model is no longer available on Segmind

Please use our selection of newer models.

Inputs

You might need to include a gender in the prompt to get the desired result

The face image to use for the generation

Preview

Examples

Default output example
--

PuLId Lightning

PuLId Lightning model is a novel tuning-free ID customization method for text-to-image generation.

By incorporating a Lightning T2I branch with a standard diffusion one, PuLID introduces both contrastive alignment loss and accurate ID loss, minimizing disruption to the original model and ensuring high ID fidelity. Experiments show that PuLID achieves superior performance in both ID fidelity and editability. Another attractive property of PuLID is that the image elements (e.g., background, lighting, composition, and style) before and after the ID insertion are kept as consistent as possible.