Shulou(Shulou.com)11/24 Report--

One of the following four pictures is by the famous Japanese artist Taku Mengji. Can you tell which one it is?

The answer is in the upper left corner, but it doesn't matter.

What is important is that the other three works with very similar styles and even nine points of resemblance are all generated by AI.

This is Stable Diffusion Reimagine XL, the latest image reconstruction tool released by Stability AI's Clipdrop.

(the name is too long, so let's call it RXL for short)

With it, you don't need any expertise or prompt, and you can get three similar works by uploading one picture.

Of course, the scope of application is not limited to painting, any picture can be operated in this way.

For example, if you want to change the layout of the room on a whim, you can also ask it to generate some effect pictures for you.

The top left of △ is the original picture, the same as below.

Netizens have also posted their ways of playing on social media topics.

For example, generate more angular "photos" for Tesla's car.

Or change the expression and movement of the character.

Landscape photos and illustrations are all good projects, and we have actually experienced them.

Landscape photos, spatial layout, and illustrations are all RXL's specialty projects.

If the landscape photos are classified and refined, they can be roughly divided into urban scenery, natural scenery and other types.

In terms of urban scenery, we used a picture of Victoria Harbour in Hong Kong as the original picture, and got three urban landscapes.

After the change of architecture, of course, it is different from the real city, but it can be used to generate a virtual city.

The reconstruction of natural scenery photos seems to be what RXL is good at.

For example, the imitation of this picture of Tianchi in Changbai Mountain is enough to make it look real.

And Chaka Salt Lake.

RXL can also be used in life, such as tidying up your desktop.

Take a picture of your desktop, upload it to RXL, and you can get a new layout.

And if you are an illustrator, RXL can also improve your productivity.

In terms of quantity, RXL can directly help you generate more paintings of the same style.

In terms of quality, if you are not satisfied with your work but do not know where to modify it, you can also try to ask RXL to help.

For example, the above works not only maintain the consistency of the style perfectly, but also have good visual effects.

In terms of works of art, we also tested them with celebrity paintings.

RXL and Van Gogh seem to have a tacit understanding, and the stars, moonlight and sunflowers are somewhat alike.

However, similarity cannot be used as the only criterion to evaluate the performance of RXL.

For paintings, it is more important to imitate the style of famous artists and create works with other contents.

Therefore, due to its nature, it is not so appropriate to use RXL to imitate famous landscapes.

The details are flawed, but you can edit RXL. There are still some flaws in the depiction of some details.

For example, when imitating Monet's impression of sunrise, there are two suns in the sky, and the colors are not the same.

The facial bones of the imitation Mona Lisa also look a little strange.

In terms of real people, the common problem with AI painting tools in hand handling seems to be unavoidable-a replica of Cook has only four fingers.

However, if you are not satisfied with the image generated by RXL, you can regenerate it with one click.

And if the local effect is still not satisfied, it can also be targeted to clean up.

But the way of cleaning up seems to be a little violent.

In addition, if you don't want the background, you can erase it with one click.

Generally speaking, RXL can be helpful in the work of photographers and illustrators, as well as in the design of life scenes.

In addition to what we think of, there will be more interesting application scenarios waiting to be explored.

In working principle, unlike the traditional AI tools, RXL directly starts its own stove to draw new pictures.

RXL encodes the pictures uploaded by users instead of text prompts in the graphic tool.

According to officials, RXL's work does not use any of the pixels in the original image.

Having said so much, can't wait to have a try?

Free users can experience it three times, and the generated image is downloaded with a watermark.

The paid version costs $7 a month, and API is available in addition to the web version.

However, you don't need to log in to the account when using the free version, so...

In addition, according to officials, the source code for RXL will be released in GitHub later.

Portal:

Https://clipdrop.co/stable-diffusion-reimagine

Reference link:

[1] https://stability.ai/blog/stability-ai-clipdrop-launches-reimagine-xl

[2] https://twitter.com/StabilityAI/status/1666114113267990528

[3] https://twitter.com/hashtag/reimagineXL

This article is from the official account of Wechat: qubit (ID:QbitAI). Author: Creasy.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.