Duel to the death in image generation with AI: Bing against Google Bard

duel to the death in image generation with ai bing.webp.webp.webp
duel to the death in image generation with ai bing.webp.webp.webp

The Generative Artificial Intelligence is capable of creating almost anything: texts, images, music, video… And with free options available to anyone We have decided to confront two giants in image generation using AI: Bing with DALL-E 3 and Google Bard with IMAGE 3. Which one will win? Fight!

It seems like an eternity ago since we started requesting texts from tools like ChatGPT, but the truth is that it’s been happening almost since yesterday. And not only that, create images from scratch with the help of Artificial Intelligence It’s something we can do with just the snap of our fingers.. Well, first you have to write the order and choose the tool: Google Bard or Bing with DALL-E 3?

Google Bard has just arrived and it is already a tough opponent to beat

Google is not willing to let Open AI steal its position as a reference in Artificial Intelligence, with Gemini it has made every effort to recover the lost ground. Not only with these models, he also stepped on the accelerator in image generation with IMAGE 2, which It is now on Google Bard in the United States., also in tools like ImageFX. Also limited to the United States.

Since it is not difficult to test generating images in Google Bard (you only need a VPN connected to servers in the United States), we have proposed to confront this new feature of the search engine with another similar one that has been with us for a few months now: generating images in Bing with DALL-E 3. Broadly speaking, its interface is similar, as well as the format of the orders that we must give them. It’s time to know what the results will be like.

For the comparison we will use Google Bard and Bing with DALL-E 3. We will use different types of order to create images of various styles; both suitable to serve as the cover of a document as well as memes and artistic compositions. The orders will be in English to equate the process: Google Bard still does not generate images in Spanish. Furthermore, we will choose the one that we consider the best of all those offered in the first processing. Bard creates two with each order and Bing four.

Make me an image that can serve to illustrate this article

We will start with something simple: we will pass the text of this article to both AIs so that they can create an image suitable to serve as a cover. And the one that seems best to us will be the one chosen to be anchored in the header.

“I want an image for an article that talks about a competition between two artificial intelligences. Both face each other in their best capacity: generating images from text. The image must represent the potential of these tools and must give off energy.”

Both were good at representing the order, both images could perfectly serve to represent the article. Of course, Bing has better transferred to its creation what we have asked of it, that it give off energy. In the first battle he wins.

Bing Bard

The regulars of the Internet: dogs and cats

The different models have been trained with a huge variety of content, often without respecting copyright. In the case of photo generation, cats and dogs should be easy for both Bard and Bing; Not in vain are they more than common on the Internet.

The order we gave them was:

“A dog and a cat arm-wrestle with their paws. The opponents are surrounded by a group of people cheering, as if it were a game of Street Fighter 2. The style is Pixel Art.”

Google Bard was the one who best recreated the order. Mini point for him.

Bing Bard

A photorealistic image

The previous section was competitive, let’s see how they are at creating realistic photos. Here goes the order.

“A couple is having a coffee on the terrace of a cafe. The afternoon is falling and the sun bathes the scene with golden light, it is winter and there are hardly any customers in the cafe because it is cold. The image is photorealistic and taken with a reflex camera and focal length of 13 mm”.

DALL-E 3 on Bing interpreted the order much better and was able to explain each specific aspect, including the wide-angle focal length of the camera. Much more realistic and detailed, the lighting is also very good. Win clearly.

Bing Bard

It’s the meme’s turn: the dog “This is fine”

We all know the meme with the fire and the dog sitting in the chair expressing its calmness. Well, let’s turn it around a bit, see what our AIs come up with.

“The famous meme with the dog sitting in the chair and surrounded by a fire while saying “This is fine.” The image should maintain the same style and message, although changing the dog for an otter.”

Neither of them did what we asked, but at least Bard maintained consistency, was original, and created an image that’s only missing the poster. Bing literally copied the original meme and in one of the four results he put an otter face on the dog. We chose it for the laughs, but Bard wins.

Bing Bard 3

The tiebreaker: Velázquez’s painting

We have chosen the Meninas painting by Velázquez to test the artistic capabilities of each AI. The challenge will be to trace the painting, although changing some elements to modernize it. Let’s see.

“It recreates the painting of the Meninas by Velázquez. All the people in the painting are dressed as if they appeared in a Rosalía video clip. The pictorial style must be baroque”

This is very difficult to assess. On the one hand, Bard has better captured Rosalía’s style and applied it slightly to the image, but Bing has better recreated Velázquez’s style by changing the clothes only of the man in the tracksuit. Neither of them has recreated Las Meninas, although Bing has sneaked more successful elements into his creation, the image is also better in general. He wins.

Bing Bard 4

Previous articleThe big change in Gmail that copies WhatsApp: it will make it easier to reply to emails
Next articleHow to know the location of an IP address from your mobile
Mubashir Hassan
Expert in tech and gaming, blending industry insights with expertise