首页
学习
活动
专区
工具
TVP
发布
精选内容/技术社群/优惠产品,尽在小程序
立即前往

四大顶流AI绘图模型真实评测 - Midjourney、Adobe、SD、DALLE

昨天,Adobe正式发布了他们新一代的AI绘图大模型:Adobe Firefly 3。

细节更强、语义理解更强、控制性更强等等。

还发了新一版本的PS AI。

不过这些不是重点。

Adobe Firefly 3的发布,结合前段时间发布的SD3,让我有了再一次搞一个AI绘图大模型竞技场,评测一下的想法。

上一次做AI绘图的综合评测还在去年12月1号:

那时候Midjourney还没发V6,stability也没发SD3。

在现在这个节点,过了近半年的时候,来再看一下现在进化过的巨头们,已经达到了什么样的水平。

四家分别为:

Midjourney V6、Adobe Firefly 3、Stable Diffusion 3、Dalle 3。

至于评测方式,我依然会从细节质量、审美(构图色彩等)、语义理解这三个维度来评测,剔除掉了风格多样化这个指标(没法测)。

细节质量、审美、语义理解每个类别14个case,总和42个Case(42这个数字的代表意义懂的都懂哈哈哈哈)

同时每个Prompt我会在AI绘图模型中roll3次出12张图,取效果最具有代表性的那个图,尽量减少偏见。同时为了保证公平,基本不会搞特别复杂的prompt。

同时,为了有最后整体可视化的评分让大家看着更直观,所以我会进行打分。在每个案例中,第一名为4分,第二为3分,第三为2分,最后一名为1分,最后计算平均分。

虽然每个case数量都不是很多,但是这也差不多了,而且是我个人的极限了。为了避免文章太长阅读体验极差,我就每个类别只放8个Case来做展示。

OK,让我们开始吧。

一. 细节质量

主要测试AI绘图对于细节的表现能力,比如人物面部皮肤的质感、比如织物纹理的细节、场景细微元素的细节等等,这个是对模型精度和输出质量一个非常重要的考量。

1.Prompt:

Selfie of charming kpop girl, outdoors, evening time, brunette, casual giggle, 2 bun tied hairstyle

Midjourney > SD3 > Adobe > Dalle

-

2.Prompt:

Portrait of a 2000s blonde woman posing on a sports car, white wired headphones, expressionless, 2000s hairstyle, 2000s fashion, sun rays, light teal and amber,Cinestill 50D

Midjourney > SD3 > Adobe > Dalle

-

3.Prompt:

Photo of smiling Labrador wearing sunglasses and straw hat sitting on the beach bench with glass of cocktail, beach scene, realistic

Midjourney > SD3 > Adobe > Dalle

-

4.Prompt:

a sports car drifting in a middle of partitions in a festival of vape and there is people around the car vaping, cinematic mood

SD3 > Adobe > Midjourney > Dalle

-

5.Prompt:

Realistic illustrations,The drumstick hits the frame and the drum bounces up water droplets

Midjourney > Adobe > Dalle > SD3

-

6.Prompt:

a house design inside of the perfect beach house, rustic malibu in style, the beach and surf included in the photos, Photography

Midjourney > Adobe > SD3 > Dalle

-

7.Prompt:

beautiful blonde model made out of porcelain, long hair, wearing sci-fi light mecha armor, in the style of balanced symmetry, white and blue LED lights on armor

Midjourney > SD3 > Adobe > Dalle

-

8.Prompt:

Delicious hamburger, floating in the air, food professional photography, studio lighting, studio background

Midjourney > Adobe > SD3 > Dalle

-

剩下case略。

在细节质量部分,Midjourney基本以绝对的优势压倒性胜利。

二. 审美

主要测试AI绘图的审美能力,一张图好不好看,是美是丑,除了细节之外,更多的还需要看模型的审美能力,比如构图、色彩、光影等等,审美强,出的图才好看。

1.Prompt:

Creatures from the Book of Mountains and Seas of China, a golden alien tiger with a resting bird on its back, attack posture, with light and golden particles emitting in the air

Midjourney > SD3 > Dalle > Adobe

-

2.Prompt:

A strong man riding a steel dragon flying in the sky, panorama, steel mecha, futuristic tech wind

Midjourney > Dalle > SD3 > Adobe

-

3.Prompt:

An abstract three-dimensional sculpture in the shape of an orchid, composed of gemstones and frosted viscous materials, in the style of tesseract, light-filled, sparkling water reflections, sunrays shine upon it

Midjourney > Adobe > SD3 > Dalle

-

4.Prompt:

woman smiling and having a cup of 7-eleven coffee outside a 7-eleven convenience store in the morning in the style of 90's anime, 1990s anime texture and colors, thick line work

Midjourney > Dalle > SD3 > Adobe

-

5.Prompt:

fantasy greatsword made from crimson metal, oil painting

Midjourney > SD3 > Dalle > Adobe

-

6.Prompt:

a dark ocean with great Sturm, Captive Souls Pirate's Redemption, ship emerging out of the fog, Giant octopus reaching out of the waters to pull down the ship

Midjourney > Dalle > SD3 > Adobe

-

7.Prompt:

warhammer 40K, Islamic space marine, white armor, black and gold trim,  matte paintin

Midjourney > SD3 > Adobe > Dalle

-

8.Prompt:

oil painting of an angel with wings spread above the forest, light beam from its eyes illuminates path in bright green and blue colors

Midjourney > Adobe > SD3  > Dalle

-

剩下case略。

在审美部分,Midjourney依然以绝对的优势压倒性胜利,而以设计起家的Adobe,反而拉了最大的跨。

三. 语义理解

主要测试AI绘图对于复杂语义的理解能力,能否将文本内容都能清晰的表达出来并保证生成图片的质量。

1.Prompt:

Portrait photograph of an anthropomorphic tortoise seated on a New York City subway train

Dalle > Midjourney > SD3 > Adobe

-

2.Prompt:

A businessman on a throne. The AI agents gathered behind him like royal guards. Photo Real

Dalle > Midjourney > SD3 > Adobe

-

3.Prompt:

A cup of coffee sitting on a table in front of a window, outside the window is a futuristic city; a futuristic monorail can be seen close by, many lush plants around, shot from ground floor, clouds above

Dalle > Adobe > SD3 > Midjourney

-

4.Prompt:

A hyper-realistic image of an anthropomorphic corn cob working as a cashier at a convenience store, depicted with a cheerful expression while laughing. The corn cob, dressed in the store's uniform, features a friendly face with eyes and a mouth on the husk, showing a big, joyful smile. The scene captures the corn cob scanning items at the cash register, wearing a typical convenience store uniform that includes a neat polo shirt and a name tag

Dalle > Midjourney > SD3 > Adobe

-

5.Prompt:

Editorial photography of astronaut cooking Christmas colorful chocolate honey cookies on spaceship, Christmas honey cookies floating around astronaut, no gravity, in spaceship, levitated

Dalle > Midjourney > SD3 > Adobe

-

6.Prompt:

a close up hyper realistic image of a medieval knight facing off against the grim reaper. Dramatic lighting

Dalle = Midjourney > Adobe > SD3

-

7.Prompt:

a very pretty young woman smilling flying over an aztec city with a dog, both the woman and the dog are flying, she is wearing an aztec outfit, the dog is wearing a colourful collar. they both seem to be having fun, ultra realistic

Dalle = Midjourney > Adobe > SD3

-

8.Prompt:

dungeons and dragons, high detailed, fantastic realism, female centaur with unicorn horn on head, hyper realistic

Midjourney > SD3 >  Dalle> Adobe

-

剩下case略。

Dalle3和Midjourney基本上处于领先地位,Dalle还是领先一筹。Adobe继续垫底。

最后总结

在四个大模型三个维度评完了以后,我相信大家应该能对这几个大模型有大概的了解了。

但是为了更直观一些,我再来做个雷达图吧。

细节质量方面,MJ V6 > SD3 > Adobe Fiefly 3 > Dalle 3。

审美方面,MJ V6 > SD3 >  Dalle 3 > Adobe Fiefly 3。

语义理解方面,Dalle 3 > MJ V6> SD3 > Adobe Fiefly 3。

MJ依然稳坐头把交椅,很多人跟我说,啥XX大模型在什么什么参数评测中已经超越了MJ啥啥的,我每次都点点头:哦。

而Adobe Fiefly 3的全面拉胯以至于我几度怀疑自己是不是选错了模型,直到我再三确认我选的确实就是Fiefly  Image 3预览版。

就...拉胯的令人难以置信。

而SD3至少在我以API方式接入使用下,也没有很多自媒体或者其他人吹的那么神乎其神。

希望这个评测,能抛砖引玉吧,让大家对AI绘图综合有一些了解。

更建议的是,自己上手去试试。

又跑了十几个小时,虽然跟大家说的是只有42个Case,但是背后跑了不知道多少。希望能对大家有所帮助吧。

  • 发表于:
  • 原文链接https://page.om.qq.com/page/Ov6AmaLbRKmnl8Re8tY1NCzQ0
  • 腾讯「腾讯云开发者社区」是腾讯内容开放平台帐号(企鹅号)传播渠道之一,根据《腾讯内容开放平台服务协议》转载发布内容。
  • 如有侵权,请联系 cloudcommunity@tencent.com 删除。

相关快讯

扫码

添加站长 进交流群

领取专属 10元无门槛券

私享最新 技术干货

扫码加入开发者社群
领券