这个脚本利用稳定的扩散v1.5从拥抱面孔的扩散器库来基于给定文本提示符生成图像变化。通过使用火炬和pil，它处理输入图像，应用ai驱动的转换并保存结果。
您可以克隆此回购以获取代码https://github.com/alexander-uspenskiy/image_variations>
源代码：
import torchfrom diffusers import StableDiffusionImg2ImgPipelinefrom PIL import Imageimport requestsfrom io import BytesIOdef load_image(image_path, target_size=(768, 768)): """ Load and preprocess the input image """ if image_path.startswith('http'): response = requests.get(image_path) image = Image.open(BytesIO(response.content)) else: image = Image.open(image_path) # Resize and preserve aspect ratio image = image.convert("RGB") image.thumbnail(target_size, Image.Resampling.LANCZOS) # Create new image with padding to reach target size new_image = Image.new("RGB", target_size, (255, 255, 255)) new_image.paste(image, ((target_size[0] - image.size[0]) // 2, (target_size[1] - image.size[1]) // 2)) return new_imagedef generate_image_variation( input_image_path, prompt, model_id="stable-diffusion-v1-5/stable-diffusion-v1-5", num_images=1, strength=0.75, guidance_scale=7.5, seed=None): """ Generate variations of an input image using a specified prompt Parameters: - input_image_path: Path or URL to the input image - prompt: Text prompt to guide the image generation - model_id: Hugging Face model ID - num_images: Number of variations to generate - strength: How much to transform the input image (0-1) - guidance_scale: How closely to follow the prompt - seed: Random seed for reproducibility Returns: - List of generated images """ # Set random seed if provided if seed is not None: torch.manual_seed(seed) # Load the model device = "cuda" if torch.cuda.is_available() else "cpu" pipe = StableDiffusionImg2ImgPipeline.from_pretrained( model_id, torch_dtype=torch.float16 if device == "cuda" else torch.float32 ).to(device) # Load and preprocess the input image init_image = load_image(input_image_path) # Generate images result = pipe( prompt=prompt, image=init_image, num_images_per_prompt=num_images, strength=strength, guidance_scale=guidance_scale ) return result.imagesdef save_generated_images(images, output_prefix="generated"): """ Save the generated images with sequential numbering """ for i, image in enumerate(images): image.save(f"images-out/{output_prefix}_{i}.png")# Example usageif __name__ == "__main__": # Example parameters input_image = "images-in/Image_name.jpg" # or URL prompt = "Draw the image in modern art style, photorealistic and detailed." # Generate variations generated_images = generate_image_variation( input_image, prompt, num_images=3, strength=0.75, seed=42 # Optional: for reproducibility ) # Save the results save_generated_images(generated_images)
import torchfrom diffusers import StableDiffusionImg2ImgPipelinefrom PIL import Imageimport requestsfrom io import BytesIOdef load_image(image_path, target_size=(768, 768)): """ Load and preprocess the input image """ if image_path.startswith('http'): response = requests.get(image_path) image = Image.open(BytesIO(response.content)) else: image = Image.open(image_path) # Resize and preserve aspect ratio image = image.convert("RGB") image.thumbnail(target_size, Image.Resampling.LANCZOS) # Create new image with padding to reach target size new_image = Image.new("RGB", target_size, (255, 255, 255)) new_image.paste(image, ((target_size[0] - image.size[0]) // 2, (target_size[1] - image.size[1]) // 2)) return new_imagedef generate_image_variation( input_image_path, prompt, model_id="stable-diffusion-v1-5/stable-diffusion-v1-5", num_images=1, strength=0.75, guidance_scale=7.5, seed=None): """ Generate variations of an input image using a specified prompt Parameters: - input_image_path: Path or URL to the input image - prompt: Text prompt to guide the image generation - model_id: Hugging Face model ID - num_images: Number of variations to generate - strength: How much to transform the input image (0-1) - guidance_scale: How closely to follow the prompt - seed: Random seed for reproducibility Returns: - List of generated images """ # Set random seed if provided if seed is not None: torch.manual_seed(seed) # Load the model device = "cuda" if torch.cuda.is_available() else "cpu" pipe = StableDiffusionImg2ImgPipeline.from_pretrained( model_id, torch_dtype=torch.float16 if device == "cuda" else torch.float32 ).to(device) # Load and preprocess the input image init_image = load_image(input_image_path) # Generate images result = pipe( prompt=prompt, image=init_image, num_images_per_prompt=num_images, strength=strength, guidance_scale=guidance_scale ) return result.imagesdef save_generated_images(images, output_prefix="generated"): """ Save the generated images with sequential numbering """ for i, image in enumerate(images): image.save(f"images-out/{output_prefix}_{i}.png")# Example usageif __name__ == "__main__": # Example parameters input_image = "images-in/Image_name.jpg" # or URL prompt = "Draw the image in modern art style, photorealistic and detailed." # Generate variations generated_images = generate_image_variation( input_image, prompt, num_images=3, strength=0.75, seed=42 # Optional: for reproducibility ) # Save the results save_generated_images(generated_images)
它的工作原理：
>加载和预处理输入图像
接受本地文件路径和url。
>将图像转换为rgb格式，并将其调整为768×768，以维持纵横比。
添加填充以适合目标尺寸。
初始化稳定扩散v1.5
>将模型加载在cuda上（如果有）或落回cpu。使用stablediffusionimg2imgpipeline处理输入映像。生成ai修改的图像变化
添加文本提示来指导转换。
强度（0-1）和引导量表（更高=更严格的提示依从性）等参数允许自定义。
每个提示支持多个输出图像。
将结果保存到图像输出目录。
>输出带有顺序命名方案的生成图像（生成_0.png，生成_1.png等）。
示例用例
>您可以使用以下提示来将一个人的图像转换为中世纪的国王提示=“在中世纪的环境中，将这个人当作强大的国王，逼真的和详细的。
初始图像：
结果：
cons＆pros
cons：
在某些硬件配置上可能会很慢。
小尺寸模型限制。
pros：>在本地运行（不需要云服务）。用于微调输出的可自定义参数。
可重现的可选随机种子。
以上就是使用稳定的扩散V上的笔记本电脑上的AI驱动图像处理 – 这比您想象的要容易！的详细内容，更多请关注创想鸟其它相关文章！
版权声明：本文内容由互联网用户自发贡献，该文观点仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。
如发现本站有涉嫌抄袭侵权/违法违规的内容， 请发送邮件至 chuangxiangniao@163.com 举报，一经查实，本站将立刻删除。
发布者：程序猿，转转请注明出处：https://www.chuangxiangniao.com/p/1355823.html
微信扫一扫 
支付宝扫一扫 
