AI-generated images are a real creative tool now, not a novelty. The question is no longer "can it look good," it's "does it belong here." That depends entirely on what the image is being asked to prove.
Get that call wrong and you don't just get a bad image, you get a trust problem, and trust problems are expensive to fix.
Where AI imagery genuinely works
AI-generated visuals earn their place when the image is illustrating a concept, not documenting a fact. Mood boards, abstract backgrounds, campaign concept art, social filler graphics, stylized textures, hero images for blog posts that aren't claiming to show a real event: all fine territory. Nobody is being asked to believe the image is a photograph of something that actually happened.
It also works well in early-stage client presentations, where you're selling a direction, not a finished product. A generated mockup of "what the campaign could feel like" is a legitimate, fast way to align on tone before real photography or design gets commissioned.
Where it quietly kills trust
The danger zone is any image that implies "this is real," when it isn't. Real people using a real product. Before-and-after results (beauty, medical, fitness, home renovation). Team photos. Customer testimonials. Storefronts, interiors, food that a customer will actually walk in and expect to see. In every one of these categories, the image isn't decoration, it's a claim, and a fabricated claim is a lie even if nobody intended it that way.
The data backs up why this matters more than it might feel like day to day. Getty Images' 2024 global report, "Building Trust in the Age of AI", drawing on over 30,000 adults across 25 countries, found that 98% of consumers agree authentic images and video are pivotal to establishing trust in a brand, yet 76% admit they can't reliably tell whether an image is real. Nearly 90% want to know when an image was AI-generated, and separately, 82% say they're skeptical of the authenticity of social media content specifically because of manipulated imagery. People can't spot the fake, but they've stopped assuming anything is real, and both of those facts should worry anyone using AI images in a high-trust context.
The report's other finding matters just as much for brand decisions: people feel less favorably toward brands they perceive as using AI-generated images of people or products. Consumers aren't neutral on this. It costs you something.
A working framework
| Use case | AI-generated image | Real photography required |
|---|---|---|
| Campaign mood board / concept pitch | Yes | No |
| Blog hero image, abstract topic | Yes | No |
| Social filler graphic, no claim implied | Yes | No |
| Product on a real customer | No | Yes |
| Before/after results (beauty, medical, home) | No | Yes |
| Team or "about us" photos | No | Yes |
| Testimonials / customer stories | No | Yes |
| Food, interiors, storefronts a customer will visit | No | Yes |
How to tell, and how to disclose
- Ask one question before generating: "is this image making a factual claim, or setting a mood?" If it's a claim, don't generate it.
- If an AI image appears anywhere near a testimonial, review, or "real client" label, that's an automatic no.
- Industries already operating under high consumer trust expectations (healthcare, financial services, travel) should assume disclosure isn't optional, per Getty's own findings.
- When in doubt, label it. A small "AI-generated concept image" caption costs nothing and matches what most of your audience already wants.
- Budget real photography for anything that will sit next to a client's name, face or actual product.
FAQ
Can I use AI images for a client's website at all? Yes, for concept work, backgrounds, abstract sections and early pitches. Not for anything presented as documentary proof of a real person, place or result.
Does labeling AI images actually hurt engagement? There's no solid public data suggesting labeling reduces performance, and Getty's research points the other way: transparency is what most consumers are actively asking for. Treat labeling as a trust investment, not a disclaimer that costs you clicks.
What about industries like beauty or medical aesthetics, where AI images seem tempting for "after" shots? Don't. That's precisely the category where a fabricated result becomes a credibility risk if discovered, and results-based industries are exactly where Getty's research shows scrutiny is highest.
Need real photography direction alongside smart use of AI concept work? Creative Hero builds both into brand and campaign work, and knows exactly where the line sits.
