python直接调用InstantID进行图片生成

项目地址 https://github.com/InstantID/InstantID

克隆到本地，根据要求pip安装依赖

模型文件上篇文章讲了如何下载 https://www.cnblogs.com/qcy-blog/p/18202276

我用的windows，所以改了一下示例infer.py源码,主要是修改了模型得绝对路径。

import cv2
import torch
import numpy as np
from PIL import Image
from diffusers.utils import load_image
from diffusers.models import ControlNetModel
from insightface.app import FaceAnalysis
from pipeline_stable_diffusion_xl_instantid import StableDiffusionXLInstantIDPipeline, draw_kps

def resize_img(input_image, max_side=1280, min_side=1024, size=None, 
               pad_to_max_side=False, mode=Image.BILINEAR, base_pixel_number=64):
    w, h = input_image.size
    if size is not None:
        w_resize_new, h_resize_new = size
    else:
        ratio = min_side / min(h, w)
        w, h = round(ratio*w), round(ratio*h)
        ratio = max_side / max(h, w)
        input_image = input_image.resize([round(ratio*w), round(ratio*h)], mode)
        w_resize_new = (round(ratio * w) // base_pixel_number) * base_pixel_number
        h_resize_new = (round(ratio * h) // base_pixel_number) * base_pixel_number
    input_image = input_image.resize([w_resize_new, h_resize_new], mode)

    if pad_to_max_side:
        res = np.ones([max_side, max_side, 3], dtype=np.uint8) * 255
        offset_x = (max_side - w_resize_new) // 2
        offset_y = (max_side - h_resize_new) // 2
        res[offset_y:offset_y+h_resize_new, offset_x:offset_x+w_resize_new] = np.array(input_image)
        input_image = Image.fromarray(res)
    return input_image

if __name__ == "__main__":
    # Load face encoder
    app = FaceAnalysis(name='antelopev2', root=f'F:\\code\\ComfyUI\\models\\insightface', providers=['CUDAExecutionProvider', 'CPUExecutionProvider'])
    app.prepare(ctx_id=0, det_size=(640, 640))
    # Path to InstantID models
    face_adapter = f'F:\\code\\ComfyUI\\models\\checkpoints\\ip-adapter.bin'
    controlnet_path = f'F:\\code\\ComfyUI\\custom_nodes\\ComfyUI-InstantID\\checkpoints\controlnet'
    # Load pipeline
    controlnet = ControlNetModel.from_pretrained(controlnet_path, torch_dtype=torch.float16)
    # 模型根据自己需求下载，必须是SDXL
    #base_model_path = 'wangqixun/YamerMIX_v8'
    base_model_path = f'F:\\cache\\hub\\models--stabilityai--stable-diffusion-xl-base-1.0\\snapshots\\462165984030d82259a11f4367a4eed129e94a7b'

    pipe = StableDiffusionXLInstantIDPipeline.from_pretrained(
        base_model_path,
        controlnet=controlnet,
        torch_dtype=torch.float16,
    )
    pipe.cuda()
    pipe.load_ip_adapter_instantid(face_adapter)

    # Infer setting
    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"
    n_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"

    face_image = load_image(f"F:\\code\\ComfyUI\\InstantID-main\\examples\\yann-lecun_resize.jpg")
    face_image = resize_img(face_image)

    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'])

    image = pipe(
        prompt=prompt,
        negative_prompt=n_prompt,
        image_embeds=face_emb,
        image=face_kps,
        controlnet_conditioning_scale=0.8,
        ip_adapter_scale=0.8,
        num_inference_steps=30,
        guidance_scale=5,
    ).images[0]

    image.save('result.jpg')