gistfile1.txt

import torch
from PIL import Image
from diffusers import StableDiffusionPipeline, StableDiffusionControlNetImg2ImgPipeline, ControlNetModel, DDIMScheduler
from diffusers.utils import load_image

controlnet = ControlNetModel.from_pretrained("DionTimmer/controlnet_qrcode-control_v11p_sd21",
                                             torch_dtype=torch.float16)

model_id = "stabilityai/stable-diffusion-2-1"
pipe = StableDiffusionControlNetImg2ImgPipeline.from_pretrained(
    model_id,
    controlnet=controlnet,
    safety_checker=None,
    torch_dtype=torch.float16
)
pipe.enable_xformers_memory_efficient_attention()
pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
pipe.to("cuda")

sd_pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16, safety_checker=None)
sd_pipe.enable_xformers_memory_efficient_attention()
sd_pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
sd_pipe.to("cuda")


def resize_for_condition_image(input_image: Image, resolution: int):
    input_image = input_image.convert("RGB")
    W, H = input_image.size
    k = float(resolution) / min(H, W)
    H *= k
    W *= k
    H = int(round(H / 64.0)) * 64
    W = int(round(W / 64.0)) * 64
    img = input_image.resize((W, H), resample=Image.LANCZOS)
    return img


# play with guidance_scale, controlnet_conditioning_scale and strength to make a valid QR Code Image

# qr code image
source_image = load_image(
    "https://s3.amazonaws.com/moonup/production/uploads/6064e095abd8d3692e3e2ed6/A_RqHaAM6YHBodPLwqtjn.png")
# initial image, anything
# init_image = load_image("https://s3.amazonaws.com/moonup/production/uploads/noauth/KfMBABpOwIuNolv1pe3qX.jpeg")
condition_image = resize_for_condition_image(source_image, 768)

prompt = "a bilboard in NYC with a qrcode"
negative_prompt = "ugly, disfigured, low quality, blurry, nsfw"

generator = torch.manual_seed(123121231)

with torch.no_grad(), torch.inference_mode():
    init_image = sd_pipe(
        prompt=prompt,
        negative_prompt=negative_prompt,
        width=768,
        height=768,
        guidance_scale=7,
        # controlnet_conditioning_scale=10.0,
        generator=generator,
        # strength=0.9,
        num_inference_steps=50,
    ).images[0]
    # init_image = resize_for_condition_image(init_image, 768)
    pipe(
        prompt=prompt,
        negative_prompt=negative_prompt,
        image=init_image,
        control_image=condition_image,
        width=768,
        height=768,
        guidance_scale=7,
        controlnet_conditioning_scale=2.0,
        generator=generator,
        strength=0.9,
        num_inference_steps=150,
    ).images[0].save("out.png")