license: mit tags:

• 图像到图像 datasets:
• yulu2/InstructCV-Demo-Data

InstructCV：作为视觉通才的指令调优文本到图像扩散模型

GitHub: https://github.com/AlaaLab/InstructCV

示例

要使用 InstructCV，请暂时使用 main 安装 diffusers。该流程将在下一个版本中可用

pip install diffusers accelerate safetensors transformers

import PIL
import requests
import torch
from diffusers import StableDiffusionInstructPix2PixPipeline, EulerAncestralDiscreteScheduler

model_id = "yulu2/InstructCV"
pipe = StableDiffusionInstructPix2PixPipeline.from_pretrained(model_id, torch_dtype=torch.float16, safety_checker=None, variant="ema")
pipe.to("cuda")
pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)

url = "在此处放入你的URL"

def download_image(url):
    image = PIL.Image.open(requests.get(url, stream=True).raw)
    image = PIL.ImageOps.exif_transpose(image)
    image = image.convert("RGB")
    return image

image         = download_image(URL)
seed          = random.randint(0, 100000)
generator     = torch.manual_seed(seed)
width, height = image.size
factor        = 512 / max(width, height)
factor        = math.ceil(min(width, height) * factor / 64) * 64 / min(width, height)
width         = int((width * factor) // 64) * 64
height        = int((height * factor) // 64) * 64
image         = ImageOps.fit(image, (width, height), method=Image.Resampling.LANCZOS)

prompt        = "检测人物。"
images        = pipe(prompt, image=image, num_inference_steps=100, generator=generator).images[0]
images[0]