FaceID-6M: A Large-Scale, Open-Source FaceID Customization Dataset
Paper โข 2503.07091 โข Published โข 3
How to use Super-shuhe/InstantID-FaceID-70K with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Super-shuhe/InstantID-FaceID-70K", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]This repository contains the InstantID-FaceID-6M model, a FaceID customization model trained on the FaceID-6M dataset, as described in the paper FaceID-6M: A Large-Scale, Open-Source FaceID Customization Dataset.
This model allows for customized face generation based on textual descriptions.