
One prompt, multiple images. It is as simple as that. Figma has just announced an update to its Make image and Edit image tools, available in Figma Design, FigJam, Figma Slides and Figma Draw: you can now generate several images from a single prompt, instead of getting just one and having to keep rewording it to get it right.
There are two ways to use this new feature, depending on what you are after.
You run a prompt and ask the same model to generate two, four or six images at once. The idea: multiply the variations of a given style so you can spot the one that fits your needs faster, without relaunching the prompt every time.
You run the same prompt across up to three different image models, in parallel. You then see how each model interprets your request, side by side, and keep whichever one you like best.
This update is part of Figma’s recent wave of generative AI announcements, alongside tools like Figma Weave, which drives image and video generation from an AI agent.
| Approach | What you get | When to use it |
|---|---|---|
| One model, several images | 2, 4 or 6 variations of the same style | To explore quickly around a validated direction |
| Several models, one image each | Up to 3 different interpretations | To compare styles before deciding |
Generating an image with AI is often a game of patience: you type a prompt, the result is not quite right, you reword it, you try again. That re-prompting loop eats up time, especially during the exploration phase, when you are still looking for the right visual direction rather than a final result.
By multiplying the options right from the first generation, Figma shortens that loop. You spend less time describing what you want and more time choosing from what is already in front of you. And the model comparison feature takes it a step further: it saves you from opening three different tabs just to test the same prompt elsewhere.
{{webdesign}}
At Mazette.co, we use Figma every day for our custom webdesign projects, and this update speaks to us directly. Generating visuals, illustrations or quick assets to dress up a mockup is part of our daily routine, and until now, every iteration meant relaunching a prompt, waiting, judging the result, then starting over.
What we particularly like is the option to compare several models in parallel. Each image model has its own touch, its own stylistic bias, its own way of handling light or composition. Being able to put them head to head on the same prompt, without leaving Figma, saves precious time during the creative exploration phase, when we are still testing directions before locking one in with the client.
One caveat though: generating more images does not replace a clear brief. A vague prompt will produce six equally vague variations. The tool speeds up iteration, but it does not excuse you from properly defining the initial intent, the visual tone, the brand reference. That is exactly where human expertise still earns its keep: knowing what to ask before asking faster.
Overall, this is good news for anyone weaving image generation into their webdesign process, as long as you keep a critical eye on whatever comes out of the machine.
Code
Impactful titles, polished meta descriptions, sitemaps, Schema.org, Hn structure, and audits: these are the SEO foundations that make your content readable by both Google AND generative AI. We cover both simultaneously.

With over 180 clients, our agency is one of the few in France to hold the Webflow Premium Partner label, supporting you in every area, including custom web design, sophisticated automation, conversion optimization, and SEO and GEO visibility.
We create bespoke web designs focused on performance, user journeys, and conversion. Join over 180 clients who have trusted us to elevate their brand.
