lucataco / ip-adapter-faceid

(Research only) IP-Adapter-FaceID can generate various style images conditioned on a face with only text prompts

  • Public
  • 30.1K runs
  • L40S
  • GitHub
  • Paper

Input

face_image
*file

Input face image

string
Shift + Return to add a new line

Input prompt

Default: "photo of a woman in red dress in a garden"

string
Shift + Return to add a new line

Input Negative Prompt

Default: "monochrome, lowres, bad anatomy, worst quality, low quality, blurry"

integer

Width of output image

Default: 1024

integer

Height of output image

Default: 1024

integer
(minimum: 1, maximum: 4)

Number of images to output

Default: 1

integer
(minimum: 1, maximum: 200)

Number of denoising steps

Default: 30

integer

Random seed. Leave blank to randomize the seed

boolean

You must agree to use this model only for research. It is not for commercial use.

Default: false

Output

output
Generated in

Run time and cost

This model costs approximately $0.0075 to run on Replicate, or 133 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 8 seconds.

Readme

Implementation of h94/IP-Adapter-FaceID

Introduction

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.

example

Limitations and Bias

  • The model does not achieve perfect photorealism and ID consistency.
  • The generalization of the model is limited due to limitations of the training data, base model and face recognition model.
  • Non-commercial use

This model is released exclusively for research purposes and is not intended for commercial use.