InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision Generalists

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

Example

To use InstructCV, install diffusers using main for now. The pipeline will be available in the next release

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 = "put your url here"

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        = "Detect the person."
images        = pipe(prompt, image=image, num_inference_steps=100, generator=generator).images[0]
images[0]