【InstantID】マルチバースの人物画像を生成できるAIで有名人をアメリカの高校生にしてみた

!git clone https://github.com/InstantID/InstantID.git
%cd InstantID/gradio_demo/
!pip install -r requirements.txt

%cd InstantID
from huggingface_hub import hf_hub_download
hf_hub_download(repo_id="InstantX/InstantID", filename="ControlNetModel/config.json", local_dir="./checkpoints")
hf_hub_download(repo_id="InstantX/InstantID", filename="ControlNetModel/diffusion_pytorch_model.safetensors", local_dir="./checkpoints")
hf_hub_download(repo_id="InstantX/InstantID", filename="ip-adapter.bin", local_dir="./checkpoints")

  .
  ├── models
  ├── checkpoints
  ├── ip_adapter
  ├── pipeline_stable_diffusion_xl_instantid.py
  └── README.md

import diffusers
from diffusers.utils import load_image
from diffusers.models import ControlNetModel

import cv2
import torch
import numpy as np
from PIL import Image

from insightface.app import FaceAnalysis
from pipeline_stable_diffusion_xl_instantid import StableDiffusionXLInstantIDPipeline, draw_kps

# prepare 'antelopev2' under ./models
app = FaceAnalysis(name='antelopev2', root='./', providers=['CUDAExecutionProvider', 'CPUExecutionProvider'])
app.prepare(ctx_id=0, det_size=(640, 640))

# prepare models under ./checkpoints
face_adapter = f'./checkpoints/ip-adapter.bin'
controlnet_path = f'./checkpoints/ControlNetModel/'

# load IdentityNet
controlnet = ControlNetModel.from_pretrained(controlnet_path, torch_dtype=torch.float16, device_map="auto")

pipe = StableDiffusionXLInstantIDPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0", controlnet=controlnet, torch_dtype=torch.float16, device_map="auto")
#pipe.cuda()

# load adapter
pipe.load_ip_adapter_instantid(face_adapter)

# load an image
image = load_image("your-example.jpg")

# prepare face emb
face_info = app.get(cv2.cvtColor(np.array(face_image), cv2.COLOR_RGB2BGR))
face_info = sorted(face_info, key=lambda x:(x['bbox'][2]-x['bbox'][0])*x['bbox'][3]-x['bbox'][1])[-1] # only use the maximum face
face_emb = face_info['embedding']
face_kps = draw_kps(face_image, face_info['kps'])

pipe.set_ip_adapter_scale(0.8)

prompt = "analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality"
negative_prompt = "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured (lowres, low quality, worst quality:1.2), (text:1.2), watermark, painting, drawing, illustration, glitch,deformed, mutated, cross-eyed, ugly, disfigured"

# generate image
image = pipe(
    prompt, image_embeds=face_emb, image=face_kps, controlnet_conditioning_scale=0.8).images[0]