FLUX.1 Lora模型：融合写实与插画风格 - 文章 - 开发者社区

你有没有想过用 AI 模型创造独特的旅行回忆？

我刚发现一个惊艳的 FLUX Lora 模型，它能将写实风格和插图风格完美融合。

想象一下，你可以用这个模型生成一张看起来像是在外面玩耍的照片，记录下你的旅行乐趣。

如果你不想露脸或想保护隐私，这个模型还能帮助你创建完美的背景图，让你的朋友圈照片更有个性。

这个模型在 FLUX.1-dev 上训练，专门为这种风格混合设计，能为你的朋友圈增添独特的亮点！

picture.image

比如下面这些例子。

凯旋门自拍 一位金发欧美女子戴着墨镜，以卡通风格展现，站在凯旋门前自拍。她的上半身图像巧妙地融合了现实与插画风格，展现出独特的艺术魅力。

picture.image A cartoon-style blonde European-American woman wearing sunglasses stood in front of the triumphant door to take a selfie, the upper body, the art style combines reality and illustration elements.

悉尼歌剧院自拍 一位卡通风格的欧洲男子在悉尼歌剧院前张开双手自拍。他的艺术风格将现实与插图元素巧妙结合，创造出富有个性的视觉效果。

picture.image A cartoon style European man opens his hands and takes a selfie under the Sydney Opera House,blending elements of reality and illustration in his artistic style.

巴黎浪漫 一位穿着精致白色碎花长裙的卡通风格欧洲女子站在埃菲尔铁塔前，蓝天背景下铁塔的标志性轮廓清晰可见。她的飘逸头发与浪漫背景相得益彰，艺术风格融合了现实和插画的元素，捕捉了巴黎的浪漫魅力。

picture.image Against the backdrop of the Eiffel Tower, a cartoon style European woman wearing a delicate white floral dress stands there, with the iconic building of the tower clearly visible under the azure sky, capturing the romantic charm of Paris. When she takes photos against this stunning background, her flowing hair adds a dreamy atmosphere, and the artistic style blends reality and illustration elements.

餐桌上的自拍 一个戴着帽子的欧美男人坐在餐桌前，用手机拍摄对面一位卡通风格的金发欧美女人。桌上摆满了色彩缤纷的食物和甜点，如水果、糕点和饮料。背景的大窗户透出自然光，营造出轻松的用餐氛围，整个场景创意地融合了现实与插画的元素。

picture.image A European and American man wearing a hat sat at the dining table,using his smartphone to capture another cartoon style blonde European and American woman across from him. On the marble table,there are various colorful foods and desserts,including fruits,pastries,and drinks. The background is a large window,where trees can be seen from the outside,and the natural light is bright,creating a relaxed dining environment. The entire scene creatively blends elements of reality and illustration. The artistic style blends elements of reality and illustration.

餐桌自拍 一位卡通风格的欧洲女子戴着眼镜，坐在现代餐厅的桌前，享受龙虾、牡蛎等海鲜。她手里拿着餐具，准备开吃。桌上摆着一杯红酒和各种美食。餐厅的背景很模糊，而插画风格与实际的食物和环境形成了鲜明对比，展现了独特的艺术效果，并且视角是从上往下的。这种风格将现实和插画元素巧妙结合。

picture.image A cartoon style European woman wearing glasses is eating a table of seafood,including lobster,oysters,and other shellfish,in a well lit modern restaurant. The background of the restaurant is very blurry,and she is holding the utensils ready to eat. There is a glass of red wine and various dishes on the table. The illustrations contrast with the real food and environment,creating a unique mixed media effect and high angle perspective. The artistic style blends elements of reality and illustration.,

这里还有更多的例子。

picture.image

怎么使用它？

模型地址 ：https://huggingface.co/Shakker-Labs/FLUX.1-dev-LoRA-blended-realistic-illustration

picture.image

如果你动手能力比较强，可以自己下载模型，自己部署。

可以选参考下面的方式


        
          
import torch  
from diffusers import FluxPipeline  
  
pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)  
pipe.load_lora_weights("Shakker-Labs/FLUX.1-dev-LoRA-blended-realistic-illustration", weight_name="FLUX-dev-lora-blended\_realistic\_illustration.safetensors")  
pipe.fuse_lora(lora_scale=1.0)  
pipe.to("cuda")  
  
prompt = "A peaceful outdoor scene,surrounded by lush green leaves and vibrant vegetation on the stone road. A cartoon style man sits on white clothes,gently caressing two animated cats,one orange and one white. Soft sunlight creates shadows,simple walls and pebble floors create a peaceful atmosphere,blending reality and animation elements,and natural and procedural characters. The artistic style blends elements of reality and illustration."  
  
image = pipe(prompt,   
             num_inference_steps=24,   
             guidance_scale=3.5,  
             width=768, height=1024,  
            ).images[0]  
image.save(f"example.png")