Menu

  • Home
  • Trending
  • Recommended
  • Latest

分类目录

  • AI 工具
  • AI新势力
  • XiaoHu.AI 学院
    • AI 教程
    • AI 课程
  • XiaoHu.AI日报
  • 开源项目案例库
    • AI 论文
    • AI 资源
    • AI 项目
XiaoHu.AI学院
  • Home
  • AI 工具
  • XiaoHu.AI 学院
    • AI 教程
    • AI 课程
  • XiaoHu.AI日报
  • 开源项目案例库
    • AI 论文
    • AI 资源
    • AI 项目
  • 加入会员
  • →社群
No Result
View All Result
  • Login
XiaoHu.AI学院
No Result
View All Result
Home AI 工具

FLUX.1-dev-LoRA:一个混合现实与插画风格模型 可以生成融合了现实与插画元素的图像

by 小互
2024年9月2日
in AI 工具, AI 项目
0 0
0
FLUX.1-dev-LoRA:一个混合现实与插画风格模型 可以生成融合了现实与插画元素的图像
0
SHARES
1.6k
VIEWS
Share on FacebookShare on Twitter

FLUX.1-dev-LoRA是一个混合现实与插画风格模型。该模型可以生成融合了现实与插画元素的图像。它基于FLUX.1-dev基础模型进行训练,特别擅长生成前景角色为插画风格,而背景为现实风格的视觉效果。

可以通过使用该模型生成图片并发布在社交平台上,如微信朋友圈或小红书,达到不露脸但仍然展示旅行场景的效果。嘿嘿..

  • 艺术风格: 模型擅长将现实与插画元素融合,创造独特的视觉效果。
  • 提示词范例: 用户可以使用详细的场景描述和人物动作提示词,生成符合自己需求的图像。

    Tip: A cartoon style man/woman, wearing what clothes, in what scene, and doing what.
    提示:卡通风格的男人/女人,穿什么衣服,在什么场景,做什么。

    The ending can add: artistic style blends reality and illustration elements. to increase the distinction between reality and cartoon.
    结局可以补充:艺术风格融合现实与插画元素。增加现实与卡通的区别。

    If it is not a famous scenic spot scene, the scene description can be slightly more detailed. If a scene does not produce the desired effect, simply change the scene. Don’t be stubborn, it is recommended to locally adjust the prompt words based on the ones used in the image return area.
    如果不是著名景点场景,场景描述可以稍微详细一些。如果某个场景没有产生所需的效果,只需更改场景即可。不要固执,建议根据图像返回区域使用的提示词进行局部调整。

    Reference 1 for prompt words:
    提示词参考1:

    A cartoon style Indian girl wearing traditional Indian clothing and a veil takes a selfie in front of the Taj Mahal, with a close-up of her upper body. Her artistic style blends elements of reality and illustration.
    一位身穿印度传统服装、戴着面纱的卡通风格印度女孩在泰姬陵前自拍,并特写了她的上半身。她的艺​​术风格融合了现实和插画的元素。

    Reference 2 for prompt words:
    提示词参考2:

    Outdoor adventure environment, with high snow peaks under partially cloudy skies and a dense evergreen forest in the foreground. In front of the forest, there is a rocky riverbed. A cartoon style man wearing glasses, wearing a white hooded sweatshirt, black shorts, green and beige backpacks, and a straw hat stands on the shore, with a cartoon style white goat next to him. The artistic style blends elements of reality and illustration.
    户外探险环境,部分多云的天空下有高高的雪峰,前景是茂密的常绿森林。森林前面有一条岩石河床。岸边站着一个戴着眼镜、穿着白色连帽运动衫、黑色短裤、背着绿色和米色背包、戴着草帽的卡通风格男子,旁边站着一只卡通风格的白山羊。艺术风格融合了现实和插画的元素。

     

  • 参数推荐: 在WEBUI在线生成时,建议的LoRA权重为0.4-0.5,而在COMFYUI在线生成时,建议的LoRA权重为1-1.2。

更多案例展示:

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.,

 

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.,

 

A man wearing a hat, sunglasses, white t-shirt, black vest, black shorts, and white sneakers squatted on a wooden path. Next to him was a cartoon style woman wearing a gray top, black skirt, and white shoes. She raised her hands above her head and leaned against a textured geometric background wall. A cartoon Doberman Inu sat next to the cartoon woman, wearing a black harness and a frisbee at her feet. The artistic style blends elements of reality and illustration.

 

In a car,a cartoon style European blonde woman sits in the passenger seat,while a man sits in the driver’s seat,holding the steering wheel with one hand. A stylish modern car with a black steering wheel,brown leather seats,and a background showcasing flowers and water bodies. On a sunny day,this car can be seen from the driver’s side window. The artistic style blends elements of reality and illustration.,

 

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.,

 

A cartoon-style blonde European and American woman wearing sunglasses standing in front of Sofia Cathedral to take a selfie,the upper body,the art style combines reality and illustration elements.,

 

A cartoon-style Indian girl,dressed in traditional Indian costumes and veil,takes a selfie in front of the Taj Mahal,artistic style blends reality and illustration elements.,upper_body,

 

A cartoon-style black man, shirtless, wearing sunglasses, gold necklace, taking a selfie on a cruise ship, behind the Statue of Liberty, artistic style blends reality and illustration elements.

 

A modern outdoor poolside scene,with a blonde European and American woman lying on an orange willow lounge chair. She is depicted as a cartoon character wearing a bikini and white sandals. The background features beige concrete walls,glass doors with curtains,and tropical palm trees. The sunlight casts shadows on the tile floor and building facade,creating a fresh and warm weather and a relaxed and peaceful atmosphere. The artistic style blends elements of reality and illustration.,

 

In front of a graffiti filled street wall in reality,a cartoon style black man wearing a black jacket,a gold necklace,and a baseball cap is taking a selfie with his phone. The artistic style blends elements of reality and illustration.,

 

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.,

 

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.

 

A cartoon-style Indian woman,praying with her hands folded under a huge Buddha statue,dressed in traditional Indian clothing,wearing a veil and beads on her hands,artistic style blends reality and illustration elements.,

 

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.,

 

On the tennis court,a cartoon style American cheerleader dances in front of an indoor basketball court,posing in a dance style that emphasizes sports. The characteristics,blurred background,and artistic style blend elements of reality and illustration.,upper_body,

 

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

在线体验:https://www.shakker.ai/modelinfo/4ea23c6ad148462589ea42e4eeac9897?from=personal_page

Related Posts

Meta AI提出了一种新的语言模型架构“Large Concept Model (LCM)  让模型更像人类思考
XiaoHu.AI日报

Meta AI提出了一种新的语言模型架构“Large Concept Model (LCM) 让模型更像人类思考

2024年12月25日
476
阿里巴巴推出QVQ-72B 一个基于Qwen2-VL-72B的新型多模态推理模型
XiaoHu.AI日报

阿里巴巴推出QVQ-72B 一个基于Qwen2-VL-72B的新型多模态推理模型

2024年12月25日
331
Fireworks AI新功能 能够将图像或PDF等非文本内容转化为LLM可理解的结构化文本
AI 工具

Fireworks AI新功能 能够将图像或PDF等非文本内容转化为LLM可理解的结构化文本

2024年12月24日
444
Hume AI推出全能文本与语音引擎 OCTAVE 根据文本实时生成特定人格特质的声音
XiaoHu.AI日报

Hume AI推出全能文本与语音引擎 OCTAVE 根据文本实时生成特定人格特质的声音

2024年12月24日
276
Anthropic 公布了一种全新的 AI 越狱技术 可以轻松破解所有前沿模型
AI 论文

Anthropic 公布了一种全新的 AI 越狱技术 可以轻松破解所有前沿模型

2024年12月23日
607
INFP:基于音频驱动的双人对话中的互动头像生成  能自动区分谁在说话,谁在听
AI 项目

INFP:基于音频驱动的双人对话中的互动头像生成 能自动区分谁在说话,谁在听

2024年12月22日
423

Recommendeds

从基础到实操 11 个人工智能顶级免费课程资源

从基础到实操 11 个人工智能顶级免费课程资源

348 VIEWS
2024年4月6日
Coconut:连续思维链 一种新的大语言模型推理方法 直接在内部思考

Coconut:连续思维链 一种新的大语言模型推理方法 直接在内部思考

359 VIEWS
2024年12月12日
Claude 3全系支持函数调用工具Tool use  可与外部系统进行交互

Claude 3全系支持函数调用工具Tool use 可与外部系统进行交互

237 VIEWS
2024年6月1日
Jina AI Reader 工具能够从任意 URL 读取 PDF 文件 并快速解析成文本

Jina AI Reader 工具能够从任意 URL 读取 PDF 文件 并快速解析成文本

496 VIEWS
2024年5月31日
Google Shopping API :抓取商品详情、评论、规格、优惠信息等

Google Shopping API :抓取商品详情、评论、规格、优惠信息等

51 VIEWS
2024年3月11日
PhotoMaker:利用多个输入图片创建人物ID表示 来生成一致性人物图像

PhotoMaker:利用多个输入图片创建人物ID表示 来生成一致性人物图像

331 VIEWS
2024年7月23日
Google开发了一种名为TimesFM的时间序列预测模型 可预测未来

Google开发了一种名为TimesFM的时间序列预测模型 可预测未来

497 VIEWS
2024年5月12日
微软发布 Co-op Translator 可以一次性将Markdown 文件和和图像翻译成多种语言

微软发布 Co-op Translator 可以一次性将Markdown 文件和和图像翻译成多种语言

244 VIEWS
2024年12月2日
SLD:图像生成模型自动校正技术 能编辑和修复各类模型生成的图像

SLD:图像生成模型自动校正技术 能编辑和修复各类模型生成的图像

24 VIEWS
2024年3月11日
FunClip :阿里巴巴开源的一款视频自动化视频剪辑工具

FunClip :阿里巴巴开源的一款视频自动化视频剪辑工具

1.8k VIEWS
2024年5月12日

Copyright (c) 2024 by Xiaohu.AI.

  • About
  • Contact

Welcome Back!

Login to your account below

Forgotten Password?

Retrieve your password

Please enter your username or email address to reset your password.

Log In

Add New Playlist

No Result
View All Result
  • Home
  • AI 工具
  • XiaoHu.AI 学院
    • AI 教程
    • AI 课程
  • XiaoHu.AI日报
  • 开源项目案例库
    • AI 论文
    • AI 资源
    • AI 项目
  • 加入会员
  • →社群
  • Login

© 2024 Xiaohu.AI

Are you sure want to unlock this post?
Unlock left : 0
Are you sure want to cancel subscription?
转到手机版