I create luxury AI campaign photography for fashion, jewelry, beauty, and lifestyle brands that need premium visuals for ecommerce, social media, websites, and advertising.
ChatGPT just added a new sketch feature to its new Images 2.5 model, so I tried it with extremely simple sketches and short prompts to see how well it could understand my intention.
And honestly, I actually like it!
This can be helpful especially when you already have a specific pose or composition in mind and want to quickly turn that rough idea into something more refined.
If you’re curious, I included a quick process video in the comments.
Do you think this new feature could be useful in your workflow?
I’ve seen a lot of posts on X about Astra’s ability to generate impressive designs from a single prompt.
TBH, I’d seen similar claims before (about other models) and then discovered that the “prompt” included a whole block of HTML, CSS, and JS 🤭
This time, though, Astra genuinely surprised me.
I already had a landing page with a defined color palette, typography, visual elements generated with Adobe Firefly. I gave Astra the landing page (.png) and just one sentence: “Generate one more section here using this text:…”
And somehow, I got 10 distinct ideas that all felt consistent with the original design - from the colours and spacing to the typography and overall visual language.
Even the new visual elements matched the texture of the ones already used on the landing page.
So far, I haven’t been able to get the same level of visual consistency from Claude.
Have you tried Astra for visual exploration?