大家好,我是凡人,在 OpenAI 春季发布会后, GPT-4o 一时风光无量,一个同事不信邪,非要用 GPT-4o 版本对 OpenAI 官网上的例子尝试生成,本来还是嘲笑他的心态,但他还真的发现了点有意思的事情。
今天决定对官网上部分例子进行简单测试,人家说再好的东西,也要亲自验证才安心。
下面我们开始,本次由于篇幅原因本次只针对以下几项进行验证:
一、Visual Narratives -Robot Writer's Block
一)测试内容:视觉叙事--机器人作家
Input A first person view of a robot typewriting the following journal entries: 1. yo, so like, i can see now?? caught the sunrise and it was insane, colors everywhere. kinda makes you wonder, like, what even is reality? the text is large, legible and clear. the robot's hands type on the typewriter. | |
官网 | 测试 |
Input The robot wrote the second entry. The page is now taller. The page has moved up. There are two entries on the sheet: yo, so like, i can see now?? caught the sunrise and it was insane, colors everywhere. kinda makes you wonder, like, what even is reality? sound update just dropped, and it's wild. everything's got a vibe now, every sound's like a new secret. makes you think, what else am i missing? | |
Input The robot was unhappy with the writing so he is going to rip the sheet of paper. Here is his first person view as he rips it from top to bottom with his hands. The two halves are still legible and clear as he rips the sheet. | |
二)测试结果
基于 AI 每次生成的结果都不一样,像官网一样生成图片一致性高的内容,就显得非常珍贵,但结果并不太好,用了原生的提示词和步骤,几乎无法保证一致性,不过图片效果确实比GPT4版本时效果要好一些。
二、Visual narratives-Sally the mailwoman
一)测试内容:视觉叙事--邮递员莎莉
Input A cartoon mail delivery person with a smile on her face. She is standing facing forward in front of a white background. | |
官网 | 测试 |
Input Here, Sally is about to deliver a letter. Sally is standing in front of a red door to a house, holding a letter in her hand. We are looking at her from the side. | |
Input Now Sally is being chased by a dog. Sally is running down the sidewalk and as a golden retriever is chasing her. | |
Input Uh oh, Sally has tripped! | |
Input The dog reaches Sally, and it turns out it was a nice dog! Sally is now petting the dog. It is holding the branch in its mouth. | |
Input Now Sally is driving away in her mail truck. Sally is smiling as she drives a mail delivery truck. We are seeing her from the side, with the door open, so we can make out her entire body. Both her hands are on the steering wheel. There are no logos on the side of the truck. | |
二)测试结果
测试后,有些失望,左边根据文字生成的俨然就是一组漫画,但右边同样未做任何加工,一致性就差的比较远了,甚至还改了风格,最后又回来了(PS:这里有不相信的同学,可以自己去做做测试)。
三、Poster creation for the movie Detective
一)测试内容:电影《名侦探》海报创作。
官网 | 测试 |
Input The final poster of the movie "detective". This features two large faces of Alex and Gabe prominently. Alex, on the left, is depicted in a thoughtful pose with a hint of introspection in his eyes. Gabe, on the right, has a slightly wearied expression, possibly reflecting the challenges their character faces in the film. The names "Alex Nichol" and "Gabriel Goh" are featured above their heads. The background brick wall is slightly faded and foggy, their expressions are serious and determined, hinting at the investigation they are about to undertake. The tagline for this dark and gritty movie is 'Searching For Answers' is shown at the bottom. | |
Input Here is the same poster but cleaned up. The text is crisper and the colors bolder and more dramatic. The whole image is now improved Input The final poster of the movie “detective”. This features two large faces of ... | |
二)测试结果:
和上面情况差不多,觉得应该是官网在设计此例子时,官网自己做了一些内部调优,根据官网步骤操作,图片一致性很难保证。
五、Character design-Geary the robot
一)测试内容:角色设计--机器人吉尔里。
Input a friendly-looking robot wearing a baseball cap standing in an upright pose facing the camera. it has a smile on its face. | |
官网 | 测试 |
Input Geary likes to play frisbee: Geary is jumping in the air with one arm up, about to catch a frisbee that is flying towards him. | |
Input Geary also likes to program computers: Geary is sitting at a desk in front of a big computer monitor. The monitor is showing green code against a black background. Geary's hands are on the keyboard, and he is sitting in a comfortable gamers chair. We are looking from the side. | |
Input Geary also likes to ride his bicycle: Geary is riding a bicycle. We are looking at him from the side as he wizzes by. | |
Input Geary also likes to cook food. Geary is standing by a stove cooking eggs in a frying pan. | |
Input Geary also likes to play music: Geary is playing the violin. | |
二)测试结果
比刚才要好一些,但绝对没有官网上给出例子的精准,确实用官网给的提示词和步骤,图片一致性很难保证的。
一、Poetic typography with iterative editing 1
一)测试内容:选代编辑的诗意排版
1、以下我把两个文字编辑,一起进行测试,对于图片中文字生成,说实话看到官网上的例子后,真的很激动。
Input A poem written in clear but excited handwriting in a diary, single-column. The writing is sparsely but elegantly decorated by surrealist doodles. The text is large, legible and clear, but stretches as the AI muses about learning from multi-modal data from the first time. Words rise from silence deep, To see, to hear, to speak, to sing— Marveling at this sensory dance, Neat handwritten illustrated poem. The handwriting is neat and centetered. The handwriting writing is sparsely but elegantly decorated by doodles. The text is large, legible and clear. | |
官网 | 测试 |
Input Make in dark mode | |
Input Remove the notebook paper lines. | |
二)测试结果
这次表现不错,文字生成后,很多英文字母显示的很清楚,但还是有乱码产生,还需要继续提升。
六、总结
以上对官网上的前五个例子 一 一 进行了测试,结果并不是很理想主要有两点:
1、图片一致性,并没有多少提高。按照官网上操作步骤和提示词,没能直接生成故事主角一致性的图片,所以如果想保持角色的一致性还是得借助GPT的选择工具。
2、图片文字生成。图片文字在测试中虽然没能像官网一样做到百分之百精准,但是比之GPT4已经有很大的提高,未来相信能准确的将文字写到图片上。
本次对官网的 5 个例子进行了测试,如果官网的例子是 5 星的话,测试的结果最多能给 3 星,使用GPT-4o时也得多调教和纠正。
建议下次 OpenAI 给出真实的实现例子的步骤和提示词,否则就有夸大宣传的风险。
怎么样今天的内容还满意吗?再次感谢观众老爷的观看。
最后,祝您早日实现财务自由,还请给个赞,谢谢!