MidjourneyV4:打破艺术界限的全新AI绘画模型

Midjourney12mos agoupdate lida
80 0 0

文章标签:关键词:Ai绘画,V4模型,重大更新

在2022年11月6日的午后,Ai绘画领域的高峰之作Midjourney软件进行了重大升级,推出了全新的V4版本。为了让大家更好地理解这次更新的强大之处,这里将为大家展示一些相关图片,让您一睹为快。

声明:

以下图片来自Midjourney官方社区

版权归原作者及MJ官方所有,严禁商用!!!

MidjourneyV4:打破艺术界限的全新AI绘画模型

MidjourneyV4:打破艺术界限的全新AI绘画模型

MidjourneyV4:打破艺术界限的全新AI绘画模型

MidjourneyV4:打破艺术界限的全新AI绘画模型

MidjourneyV4:打破艺术界限的全新AI绘画模型

MidjourneyV4:打破艺术界限的全新AI绘画模型

MidjourneyV4:打破艺术界限的全新AI绘画模型

我们来看看官方公告:

今天,我们大家都要一起尝试测试我们的V4算法版本alpha。

在您提供提示或选择“V4”之前,请将设备切换至类型–v 4。

Whats new with the V4 base model?

在广袤的知识领域中,我们对于生物、地理和其他方面的认知远比想象中的更为丰富。

在各种情况下,表现得更擅长捕捉细节。

As an advanced article writing professional, I am adept at managing intricate prompts that involve multiple layers of specificity.

在多对象/多角色的场景中,表现更为出色。

As an article writing expert, I can rephrase the given content in a more sophisticated manner. The original text mentions advanced functionalities such as image prompting and multi-prompts. To enhance the complexity and depth of the topic, I suggest incorporating the following elements into the article:1. Explain the concept of image prompting and its significance in content creation.2. Elaborate on the benefits of using multi-prompts for generating diverse and engaging articles.3. Provide examples of real-life scenarios where image prompting and multi-prompts have proven to be effective.4. Discuss the potential drawbacks of these advanced functionalities and how to mitigate them.5. Offer insights on how to effectively integrate image prompting and multi-prompts into the content creation process.

– Supports –chaos arg (set it from 0 to 100) to control the variety of image grids

Whats new with the V4 upsampler?

– New upsampler adds/changes/corrects details in the original image (more like the v3 upscaler)

– New upsampler is an early work-in-progress (it will change significantly)

What are we working on still?

– We will increase the resolution, quality and controllability of upscaling

– We will add custom aspect ratios (currently limited to 1:1)

– We will continue to increase image sharpness and reduce instances of tight cropping

– Greatly reducing text artifacts (certain prompts become unreadable language on images)

– Were going to improve the default styling

Please note: This is an alpha test. Do not rely on any specific quirks or consistency in V4 yet. Well be pushing significant changes as we move towards full-launch.

Community Standards:

– This model can generate much more realistic imagery than anything weve released before.

– From now on, we will be much more strict with our rules around “dont be a jerk or create images to cause drama”

More about V4: V4 is an entirely new codebase and totally new AI architecture. Its our first model trained on a new Midjourney AI supercluster and has been in the works for over 9 months. V4 isnt the final step, but our first step, and we hope you all feel it as the new beginning of something deep and unfathomable.

Please use these incredible powers with joy, and wonder, responsibility and respect

Were genuinely excited to see what everyone creates.

Have fun! ❤️

翻译版:

大家好,今天我们将尝试阿尔法测试我们的V4算法版本

要打开它,请在提示后键入–v 4,或从/settings中选择“V4”

V4基本型号有什么新功能?

-更多的知识(关于生物、地点等)

-更好地处理小细节(在所有情况下)

-处理更复杂的提示(具有多个详细级别)

-多对象/多角色场景效果更好

-支持图像提示和多提示等高级功能

-支持–chaos arg(将其从0设置为100)以控制图像网格的种类

V4上采样器有什么新功能?

-新的上采样器添加/更改/更正原始图像中的细节(更像v3上采样机)

-新的上采样器是正在进行的早期工作(它将发生重大变化)

我们还在做什么?

-我们将提高升级的分辨率、质量和可控性

-我们将添加自定义纵横比(目前限制为1:1)

-我们将继续提高图像清晰度,减少裁剪过紧的情况

-大幅减少文本伪影(某些提示在图像上变成不可读的语言)

-我们将改进默认样式

请注意:这是阿尔法测试。不要依赖V4中的任何特定怪癖或一致性。随着全面推出,我们将推动重大变革。

社区标准:

-这个模型比我们之前发布的任何模型都能生成更逼真的图像。

-从现在起,我们将更加严格地遵守我们的规则,即“不要做一个混蛋或创造形象来引发戏剧”

更多关于V4:V4是一个全新的代码库和全新的AI架构。这是我们第一个在新的中程AI超级星团上训练的模型,已经投入工作9个多月了。V4不是最后一步,而是我们的第一步,我们希望大家都能感觉到它是一个深不可测的新开始。

请带着喜悦、好奇、责任和尊重来使用这些不可思议的力量

看到每个人都创造了什么,我们真的很兴奋。

玩得高兴❤️

经小编测试,最近的V4模型所生成的图像,几乎没有任何逻辑错误,也就是说,Midjourney的V4模式所生成的图像,已经可以正式投入成熟的商业使用!这意味着什么?

如果说,我们之前说Ai绘画不可能改变现有绘画行业,那么现在,实打实的说,绘画这个行业,普通的从业者,将迎来最大的一波从业危机!

如果说,人工智能,能切切实实的改变人们原有的生活,那么,最先感受到变化的,我想,应该是绘画这个领域。

– End –

关注我,了解A绘画最新动态

关键词:Ai绘画,V4模型,重大更新

© Copyright notes

Related posts

No comments

No comments...