Learn From My Worst AI Images and Fix These Biggest AI Fails

I spend more time using AI image generators than the average person. I've reviewed several programs, ranked and crowned the best of them and I've learned the best practices for AI image prompt engineering to get better results. Throughout all this, I've generated hundreds of AI images. Some images are beautiful and stunningly detailed, while others are terrible. Otherwise, they may be weird, quirky, frightening or unusable for another reason.

Every bad AI image is unique in its own way, but throughout my testing and reviewing, I've found similar problems across different services. There are certain details AI image generators are prone to mess up, and there are certain tricks you can use to fix them. None of these strategies are perfect -- they'll depend heavily on the generator you're using -- but they're a good starting point. 

Remember that no AI art service can replicate or replace human creators. If you're using AI image generators, here are the biggest problems I found and how to fix them.

Human faces and expressions

Katelyn Chedraoui via Canva Magic Media AI/CNET

Accurate facial expressions continually challenge AI generators. Quirky eyes, teeth and eyebrows are some of the strongest indicators that an image is AI-generated. In this case, the result was extremely funny to me, if also completely unusable. The girls are sporting some Halloween-like vampire teeth, and the dude in the back is having more than a bad hair day.

Stephen Shankland via Dall-E 3/CNET

Even with cartoon or non-realistic characters, generators struggle to moderate emotion and expressions. This image -- created by our best pick, Dall-E 3 -- over-amplified the prompt, and the end result was too dramatic. I'm a self-identified neat freak, but I can't imagine anyone getting this upset over what looks like hundreds of dollars of cleaning supplies. Even the best programs can fail and produce wonky results.

How to fix it: I recommend asking the service to cut down on the number of people it's trying to render -- cut down on the number of chances for error -- and using post-generation editing tools to select specific parts of the image that need regenerated or fixed. Picking a more mild adjective ("angry" rather than "enraged") might help guide the service down the right path.

Iconic characters, trademarks and recognizable logos

Katelyn Chedraoui via Canva Magic Media AI/CNET

For many reasons, AI image generators can rarely produce accurate logos, known trademarks or otherwise recognizable characters. This is usually because there are significant legal concerns about a company allowing its brand materials or intellectual property to be used for AI services. It also could be because the logo or brand you want to include isn't in the generator's training data, so the generator won't understand your request.

Two recent exceptions to this are new image generation features on the Google Pixel 9 and Pixel 9 XL, thanks to Gemini AI, which our mobile experts used to create images featuring accurate-looking Mickey Mouse and Pikachu renditions. The other exception is some paying X (formerly Twitter) users reporting that they can use the social media site's Grok chatbot to make realistic-looking Mickeys and human political figures. These images still aren't perfect renderings, but they're pretty close.

How to fix it: You can't, but on the plus side, you're a lot more likely to avoid lawsuits for copyright infringement. If you run into this issue, I recommend rethinking your design concept to see if you can get the same point across without using a specific company name or logo. Do you really need the TikTok logo, or do you just need a phone with a vertical video playing, for example.

Overlapping, complex elements

Katelyn Chedraoui via Leonardo AI/CNET

Occasionally, you'll stump a generator if you have too many overlapping or complex elements within an image. The best AI image programs aren't going to run into this issue very often, but even the best programs fail at some point. With this Leonardo image, the library of my dreams is ruined by the rolling ladder that disappears halfway up.

Katelyn Chedraoui via Canva Magic Media AI/CNET

Similarly, this photorealistic image of a kitchen looks alright from a cursory look, but a second glance or quick zoom-in shows nonsensical characters printed on the cookbook, and the book itself seems to have two spines and three sections. Images like this show how frustrating it can be to create AI images -- even when you think you've got a winner, small flaws make them unusable.

How to fix it: Try simplifying your prompt or using post-generation editing tools to single out the problem and fix it. Sometimes changing the aesthetic can help as well; these issues usually pop up when you're trying to make photorealistic or stock images. If your service offers a specific area editing tool, try using that to select the questionable area and ask the generator to remove what's in it.

Over-editing and hallucinations

Katelyn Chedraoui via Midjourney AI/CNET

The sign of a great AI image generator is its ability to produce an image with few errors or hallucinations while giving you the right tools to fix those issues when they inevitably pop up, but not every service does. In this example from Midjourney, I went through several rounds of edits on this image of a soccer team celebrating a victory, and I have no idea what happened to get to this final result -- or any clue what's going on with the blob that's presumably a player in the right-hand side of the picture. Frankly, I don't think Midjourney knew either.

How to fix it: With editing AI images, sometimes less is more. Don't be afraid to scrap your current batch of images and start over. You can often preemptively fix big issues by refining your prompt so you only have to worry about fixing minor issues later.

AI generators still need human work

Katelyn Chedraoui via Leonardo AI/CNET

I have no doubt that the companies behind these AI generators are working to eliminate these issues and level up their models. For now, imperfect images show us once again that while this tech is improving, it's not flawless. My hope is that because so many of these services face similar challenges, they will all be chasing solutions for these issues.

As a final note, I'll remind you that it's a best practice to credit or acknowledge that an image is AI-generated when you share it. As AI images get better and more realistic-looking, it's more important than ever to distinguish AI-generated art from other kinds of media.

For more, check out our advice for writing the best AI image prompt and our best picks for AI image generators.