h94/IP-Adapter-FaceID

Text To Image·h94· 170.8K· 1.9K

diffusers Text To Image arxiv:2308.06721region:us

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.

Open in MLForge Sign up free Desktop app Source ↗

# pull & run locally
pip install mlforge-sdk && mlforge pull h94/IP-Adapter-FaceID

Model details

Task

Text To Image

Provider

h94

Framework

diffusers

Size

6.5 GB

Downloads

170.8K

Likes

1.9K

Paper

arXiv:2308.06721

Updated

2024-04-16

About h94/IP-Adapter-FaceID

Related Text To Image

S stable-diffusion-v1-5/stable-diffusion-v1-5 Text To Image 1.8M 1.2K 🤗 HF S stabilityai/stable-diffusion-xl-base-1.0 Text To Image 1.3M 7.9K 🤗 HF D Lykon/dreamshaper-7 Text To Image 1.0M 63 🤗 HF Z Tongyi-MAI/Z-Image-Turbo Text To Image 887.4K 4.9K 🤗 HF S stabilityai/sd-turbo Text To Image 663.3K 455 🤗 HF S stabilityai/sdxl-turbo Text To Image 641.4K 2.6K 🤗 HF

Browse all Text To Image models →