Create & Edit Images Instantly with Grok Imagine

Try Grok Imagine
Skip to main content
- huchenlei-PuLID thumbnail

Huchenlei-PuLID

by ModelsLab
huchenleipulid
Text to Image Community ModelFree for Premium UsersLLMs.txt

PuLID is an ip-adapter alike method to restore facial identity. It uses both insightface embedding and CLIP embedding similar to what ip-adapter faceid plus model does. However, there is an extra process of masking out the face from background environment using facexlib before passing image to CLIP. PuLID also uses Eva CLIP instead of normal CLIP. In the attn overrides, PuLID also does something more than IPAdapter, as it zero pads the tensor and adds to ortho of hidden states.

PuLID uses both evaclip embedding and insightface embedding as proj module input. So in order to use the feature, you need to install https://github.com/huchenlei/sd-webui-controlnet-evaclip extension.

ComfyUI implementations:

Original repository: https://huggingface.co/huchenlei/ipadapter_pulid

API PlaygroundAPI Documentation

Input

Select models...

Per image generation will cost 0.0047$
For premium plan image generation will cost 0.00$ i.e Free.

Output

Idle

Unknown content type

Related Models

Discover similar models you might be interested in

Nahida V1.0 (LoRA on AnimagineXL4.0) - v1.0

Nahida V1.0 (LoRA on AnimagineXL4.0) - v1.0

Unicron from Transformers G1 (Pony/SDXL/IL) - SDXL

Unicron from Transformers G1 (Pony/SDXL/IL) - SDXL

citywall - V1

citywall - V1

albedobasexlv31

SolidShadow - v0.1

SolidShadow - v0.1

Ye Shunguang 3in1 - v1.0-SDXL

Ye Shunguang 3in1 - v1.0-SDXL

Night Sky V3 - V3

Night Sky V3 - V3

Hubble Telescope LoRA - Beta

Hubble Telescope LoRA - Beta

prestam - V1

prestam - V1

Converse Lugged Heel Platform - V1

Converse Lugged Heel Platform - V1

gothluna - V1

gothluna - V1

CLO_boots_v1 - V1

CLO_boots_v1 - V1