6 suggestions, tips, and prompts for creating photos with Grok AI

When X, formerly Twitter , launched Grok 2 , the AI grew to become rapidly recognized for its snarky humorousness and its means to generate photos with fewer restrictions than different platforms. However, Grok 2 additionally tends to generate extra lifelike photos than competitors like DALL-E . That, blended with the $8 month-to-month entry to X Premium that is still decrease than Google and ChatGPT’s $20 a month AI subscriptions, has earned the software program a status earlier than even leaving beta.

Nonetheless, benefiting from the platform’s capabilities requires a little bit of know-how to get one of the best outcomes. Like most AI platforms, the way you phrase the immediate issues. However, with Grok’s looser restrictions, customers ought to perceive not simply learn how to use the AI, however learn how to use the AI in probably the most moral approach doable.

Earlier than you begin typing in that immediate field, these 6 tips and suggestions will assist you to benefit from the brand new X AI.

1 Be conscious of AI ethics

Grok can do issues it most likely should not…

X / Grok

X describes Grok as an AI with “a splash of insurrection,” which loosely interprets right into a chatbot that has fewer guidelines, significantly regarding picture technology. Not like DALL-E or Google Gemini , Grok can generate photos of recognizable folks, replicate the fashion of a selected artist and even a selected piece of art work, and reproduce different mental property together with logos and licensed characters.

However, simply because Grok can do these issues doesn’t suggest you ought to. Even when wielding Grok and a keyboard as an alternative of a paintbrush, you danger lawsuits infringing on mental property when replicating an artist or together with issues like logos or licensed characters. Creating photos of recognizable folks might danger violating Right of Publicity in relevant states, laws that stops somebody’s likeness from being commercially exploited.

Some may select to keep away from AI in any respect — or be selective on which platforms to make use of — over concern with how the coaching knowledge was gathered. Artists have beforehand taken AI firms to courtroom over utilizing their work to coach knowledge. xAI says Grok 1’s initial training data got here from “a wide range of textual content knowledge from publicly out there sources from the web,” however it would not specify the place its picture coaching knowledge got here from. Grok 2 makes use of the FLUX 1 mannequin by Black Forest Labs, which is equally unclear on the place the coaching knowledge originated from. The inclusion of “signatures” in generated art work suggests copyrighted work could also be a part of the information.

The ethics of utilizing any AI platform apply to Grok as effectively, together with correctly labeling the picture as AI generated.

2 Embrace Grok 2’s strengths and perceive its weaknesses

Keep away from asking for photos with close-ups of fingers or graphics with textual content

The important thing to getting one of the best outcomes from any AI is to grasp the platform’s strengths and weaknesses, and Grok isn’t any exception. Grok’s strengths lie in its extra lifelike picture technology, its means to deal with duties like producing photos that seem like celebrities, and its deal with humor. When evaluating Grok to DALL-E, I’ve discovered Grok produced photos that had been extra lifelike (although nonetheless had a couple of tell-tale AI indicators).

However, Grok 2 is a younger program nonetheless in beta, and it has some limitations, regardless of its status for having looser content material pointers. Whereas Grok itself will inform you that it is multimodal, it is not, or a minimum of not but. There is not an possibility to connect a picture to ask Grok so as to add one thing to it or generate one thing primarily based on that file. It is a text-only enter at the moment.

Whereas Grok usually delivered photos that regarded extra superior than DALL-E, the AI nonetheless faltered at among the duties that appeared to be universally troublesome for AI. Fingers and fingers can usually look wonky. Textual content is usually gibberish and even made up of non-letters except you explicitly spell out what to say.

There are additionally some directions that Grok would not appear to grasp but. For instance, I could not get Grok to generate a picture in a selected facet ratio, regardless of explicitly asking for 16:9, I needed to go in and crop to that format afterward as an alternative. When asking for photos of individuals, Grok tends to make all of them seem like runway fashions except requested in any other case.

3 Write particular prompts, somewhat than generic

The extra detailed, the higher

X / Grok

Like most AI platforms, Grok delivers one of the best outcomes when given a selected, well-worded immediate somewhat than a generic one. As you sort within the textual content field, transcend simply what folks or objects must be within the picture. Think about elements like:

• Model: Grok can create photos that look lifelike, or you’ll be able to ask for a cartoon or perhaps a portray. Think about if you’d like brilliant, daring colours, or extra muted tones.
• Temper: Specify what kind of tone you’re searching for, whether or not you desire a humorous picture, a darkish depiction, or maybe one thing skilled.
• Background or location: Inform Grok the place this image must be situated to be able to get a background that matches your imaginative and prescient. Be particular with settings, like a espresso store or a busy avenue.

4 Ask for tweaks till you get one of the best consequence

Grok takes your prompts in context

Grok would not overlook your earlier immediate, which implies in case you don’t get an excellent consequence, you’ll be able to inform the AI extra particulars. You do not have to re-type the immediate. As a substitute, say, “Regenerate that however with _____.” If you do not have extra textual content to make clear the consequence with, you’ll be able to hit that round arrow key beneath the unique technology to regenerate from the identical immediate.

Some phrases additionally work higher than others, so you could need to experiment with rewording your immediate, somewhat than including extra particulars. After I requested for a “numerous” group for instance, it generated a picture of individuals all with the identical darkish pores and skin tone. As soon as I requested for “a wide range of pores and skin tones,” then the AI created a bunch of ethnically numerous folks.

On the flip aspect, if you wish to create a completely new picture, typically Grok will nonetheless pull particulars from the earlier immediate, just like the background or fashion that you simply requested earlier. If this occurs, merely begin a brand new chat thread so Grok “forgets” your earlier requests.

5 Have enjoyable with Grok’s snarky humorousness

Grok was made to be a much less severe AI

X / Grok

X’s new AI is understood for each its free content material pointers and its humorousness. Embrace the humorous aspect of Grok as you experiment. Grok isn’t a digital camera, so create off-kilter pairings that you simply wouldn’t see in actual life to make an announcement, like a sandwich with a aspect of on line casino “chips” or a sensible rendering of the expression “raining cats and canine.”

6 Test your privateness settings

X can use your knowledge to tweak Grok

According to X, Grok was pre-trained on a wide range of knowledge pulled from the web, not public X posts or Tweets. Nonetheless, a data-sharing setting is now mechanically turned on by default for X customers, except they opt-out. This setting says that “we might make the most of your X posts in addition to your consumer interactions, inputs, and outcomes with Grok for coaching and fine-tuning functions.”

If you do not need Grok to be skilled in your posts you’ll be able to choose out by tapping the three-dot or extra menu, deciding on Settings & Privateness, clicking Privateness and Security, then deciding on Grok. Then, uncheck the field to opt-out.

Grok additionally makes use of public Tweets to share real-time knowledge with customers. If you do not need your posts probably popping up in Grok, you may have to make your account non-public by going to Settings and Privateness > Privateness & Security > Viewers and Tagging > Shield your posts.