---
title: IP-Adapter-FaceID
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/IP-Adapter-FaceID"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/IP-Adapter-FaceID.md"
repository: AI-ModelScope/IP-Adapter-FaceID
last_updated: 2023-12-26
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
parameters: 25.5M
tensor_type:
  - F16
library_name:
  - pytorch
  - lora
  - safetensors
frameworks:
  - Pytorch
language:
  - en
downloads: 2054
stars: 8
tags:
  - text-to-image
  - stable-diffusion
---

# IP-Adapter-FaceID

> IP-Adapter-FaceID - AI-ModelScope 在 ModelScope 开源的模型。IP-Adapter-FaceID Model Card

- **Repository**: AI-ModelScope/IP-Adapter-FaceID
- **Tasks**: text-to-image-synthesis
- **Parameters**: 25.5M
- **Tags**: text-to-image, stable-diffusion
- **Downloads**: 2054
- **Stars**: 8
- **Last updated**: 2023-12-26

Source: https://www.modelscope.cn/models/AI-ModelScope/IP-Adapter-FaceID

---

# IP-Adapter-FaceID Model Card


<div align="center">

[**Project Page**](https://ip-adapter.github.io) **|** [**Paper (ArXiv)**](https://arxiv.org/abs/2308.06721) **|** [**Code**](https://github.com/tencent-ailab/IP-Adapter)
</div>

---



## 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. 

![results](./ip-adapter-faceid.jpg)

## Usage

Firstly, you should use [insightface](https://github.com/deepinsight/insightface) to extract face ID embedding:

```shell
pip install mxnet
pip install insightface>=0.2
pip install ip_adapter
```

```python
import cv2
from insightface.app import FaceAnalysis
import torch
from diffusers import StableDiffusionPipeline, DDIMScheduler, AutoencoderKL
from ip_adapter.ip_adapter_faceid import IPAdapterFaceID
from PIL import Image
from modelscope import snapshot_download

app = FaceAnalysis(name="buffalo_l",root="/root/.insightface/models" ,providers=['CUDAExecutionProvider', 'CPUExecutionProvider'])
app.prepare(ctx_id=0, det_size=(640, 640))

image = cv2.imread("/mnt/workspace/yk_dir/person.jpg")
faces = app.get(image)

faceid_embeds = torch.from_numpy(faces[0].normed_embedding).unsqueeze(0)

base_model_path = "AI-ModelScope/Realistic_Vision_V5.1_noVAE"
local_base = snapshot_download(base_model_path,revision='master')

vae_model_path = "zhuzhukeji/sd-vae-ft-mse"
local_vae = snapshot_download(vae_model_path,revision='master')

local_ip = snapshot_download("AI-ModelScope/IP-Adapter-FaceID",revision='master')

ip_ckpt = local_ip+"/"+"ip-adapter-faceid_sd15.bin"
device = "cuda"

noise_scheduler = DDIMScheduler(
    num_train_timesteps=1000,
    beta_start=0.00085,
    beta_end=0.012,
    beta_schedule="scaled_linear",
    clip_sample=False,
    set_alpha_to_one=False,
    steps_offset=1,
)
vae = AutoencoderKL.from_pretrained(local_vae).to(dtype=torch.float16)
pipe = StableDiffusionPipeline.from_pretrained(
    local_base,
    torch_dtype=torch.float16,
    scheduler=noise_scheduler,
    vae=vae,
    feature_extractor=None,
    safety_checker=None
)

# load ip-adapter
ip_model = IPAdapterFaceID(pipe, ip_ckpt, device)

# generate image
prompt = "photo of a woman in red dress in a garden"
negative_prompt = "monochrome, lowres, bad anatomy, worst quality, low quality, blurry"

images = ip_model.generate(
    prompt=prompt, negative_prompt=negative_prompt, faceid_embeds=faceid_embeds, num_samples=4, width=512, height=768, num_inference_steps=30, seed=2023
)

images[0].save("woman.png")
```


## 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.**