untuned_photorealistic_images_square.py

from diffusers import DiffusionPipeline, StableDiffusionXLImg2ImgPipeline

device = "cuda" # cpu or cuda

pipeline = DiffusionPipeline.from_pretrained(
    model_name_base,
    torch_dtype=torch.float16,
).to(device)

refiner = StableDiffusionXLImg2ImgPipeline.from_pretrained(
    model_name_refiner,
    torch_dtype=torch.float16,
).to(device)

# optional descriptive terms: sleek, futuristic, metallic, colorful, urban
subject_prompt = """photo of an electric scooter, modern, daytime, vivid cityscape"""

subject_negative_prompt = """person, people, human, rider, floating objects, text, 
words, writing, letters, phrases, trademark, watermark, icon, logo, banner, signature, 
username, monochrome, cropped, cut-off"""

refiner_prompt = """ultra-high-definition, photorealistic, 8k uhd, high-quality, 
ultra sharp detail"""

refiner_negative_prompt = """low quality, low-resolution, out of focus, blurry, 
grainy, artifacts, defects, jpeg artifacts, noise"""

for seed in range(10):
    generator = torch.Generator(device).manual_seed(seed)
    base_image = pipeline(
        prompt=f"{subject_prompt}, {refiner_prompt}", 
        negative_prompt=f"{subject_negative_prompt}, {refiner_negative_prompt}",
        num_inference_steps=80,
        generator=generator,
        height=1024,
        width=1024,
        output_type="latent",
    ).images[0]
        
    refined_image = refiner(
        prompt=refiner_prompt, 
        negative_prompt=refiner_negative_prompt,
        num_inference_steps=20,
        generator=generator, 
        image=base_image,
    ).images[0]

    refined_image.save(f"./generated_images/base_model_scooter_photo_square_{seed}.png")