fine_tuned_bw_marker_renderings.py

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

pipeline.load_lora_weights(
    project_name, 
    weight_name="pytorch_lora_weights.safetensors"
)

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

subject_prompt = """oue, marker rendering of oue electric scooter, concept art, 
futuristic cityscape, high contrast, black and white, black marker, marker drawing, 
sketch, monochromatic illustration, illustrative, graphic, muted, expressive strokes"""

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

refiner_prompt = """sharp, crisp, in-focus, uncropped, high-quality"""

# we don't want a photographic image
refiner_negative_prompt = """photographic, photo, photorealistic, 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=100,
        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/finetuned_scooter_bw_render_square_{seed}.png")