Figma AI (Make / First Draft)
Figma's AI turns the design tool into a generator: First Draft produces editable screens from a prompt using Figma-built libraries, with generation on your own design system not yet available, Make converts designs and descriptions into interactive prototypes and working front-end code, and smaller assists handle content replacement, image cleanup and smart search across files.
The output is the point: not pictures of interfaces but real Figma files and structured code, editable by designers and usable by engineers. That keeps AI work inside the team's existing system rather than beside it.
It accelerates drafts and mechanical revisions; finished production design still comes from designers refining what it starts.
- Cost
- Freemium (Free tier + paid plans)
- Ease
- Model
- Hosted service
- Checked
- August 2026
Prices, plans and model versions change fast: this is a mid-2026 snapshot; check the tool's official site for the latest.
Best for
- Editable first-draft screens generated from Figma-built libraries
- Prompts to interactive prototypes without leaving Figma
- Design-to-code handoff as an engineering starting point
- Mechanical revisions executed by prompt
- AI that lands in real files, not flat mockups
Less suited to
Figma AI drafts and accelerates; it does not finish. Production-quality design still needs a designer's judgement on hierarchy, accessibility and craft, and generated code is a starting point for engineering rather than a shippable front end.
Teams without a design system also get less: the generation quality leans on the structure you already have.
Costs & data, in short
Figma's AI capabilities, including Make, come with paid Figma plans, with allowances varying by tier. For teams already paying for Figma the increment is modest; it is not sold standalone.
Designs and prompts stay within Figma's platform terms, with admin controls on AI features for enterprise plans. Make output is a prototype starting point, not production code, so review before anything ships.
Plans
| Starter | Free |
|---|---|
| Professional | $16per user, per monthbilled annually; $20 per user per month if billed monthly |
| Organization | $55per user, per monthbilled annually |
| Enterprise | $90per user, per monthbilled annually |
Prices as of August 2026. Prices and plans change regularly. Check with the provider before you buy.
In practice
How Figma AI (Make / First Draft) is used, area by area.
Jobs
Design & creative
Figma's AI accelerates designers inside the tool that defines the profession
Figma's AI accelerates designers inside the tool that defines the profession. First Draft generates starting layouts from Figma-built libraries, with generation on your own design system not yet available by Figma's own account, Make grounds prototypes in the libraries you enable, prompt-driven edits absorb the mechanical revisions, Make turns designs into living prototypes without a handoff, and the smaller assists handle content replacement, image cleanup and search across files. The tedious stretches compress; the taste stays yours. Designers working in Figma daily, crowded by mechanical work, are the audience. AI drafts are scaffolding rather than signature: distinctive visual identity still comes from the designer, heavy reliance on generation flattens work toward the average of what the model has seen, and a plausible first draft should never skip the critique a human draft would face.
Example tasks
- Generate first-draft layouts grounded in your design system
- Execute mechanical revisions by prompt instead of by hand
- Turn designed flows into interactive prototypes with Make
- Prepare assets with built-in AI image cleanup on the canvas
- Find the right component or file with AI-powered search
Limits
AI drafts are scaffolding, not signature: distinctive visual identity still comes from the designer, and heavy reliance on generation flattens work toward the average of what the model has seen.
Compares
| vs | Pick Figma AI (Make / First Draft) when | Pick the other when |
|---|---|---|
| CanvaFull comparison → | Figma AI serves professional product design in a design-system world | speed and accessibility for non-designers matter more than precision |
| v0Full comparison → | Figma keeps the work in design space for iteration and testing | engineering-ready code is the deliverable |
| Flux (Black Forest Labs)Full comparison → | Figma AI (Make / First Draft) generates first-draft layouts grounded in your own design system rather than a generic reinterpretation of it | a consistent trained style matters more than a friendly interface |
| KreaFull comparison → | Figma AI (Make / First Draft) turns designed flows into interactive prototypes with Make, so the work becomes testable without a handoff | generation should respond like a tool in hand, not a slot machine |
| Microsoft DesignerFull comparison → | Figma AI (Make / First Draft) absorbs the mechanical revisions by prompt instead of by hand, so the tedious stretches compress and the taste stays yours | the visual need is quick and routine, and the budget conversation is best avoided |
Founders & entrepreneurs
Figma's AI lets founders produce credible product design before the design hire
Figma's AI lets founders produce credible product design before the design hire. First Draft lays out screens from a description, Make turns them into clickable prototypes investors and users can actually try, and the work accumulates in real Figma files your first designer will inherit rather than replace, which is the quiet difference from generating throwaway mockups elsewhere. It fits founders whose product needs to look designed while the design budget is zero. AI drafts start conversations rather than finish products, shipping-quality polish still wants human design sense, and a clickable demo reads as nearly-built to non-technical audiences, so caption the gap before it becomes a promised ship date. Non-visual founders may move faster in the app builders that skip design entirely.
Example tasks
- Generate first-draft product screens from a written description
- Turn concepts into clickable prototypes for user tests and investor demos
- Iterate the design language before committing to a build
- Hand a real Figma file to your eventual first designer
- Take the prototype's generated code as the build's starting point
Limits
AI drafts start conversations rather than finish products: shipping-quality visual polish still wants human design sense, and non-visual founders may move faster in the app builders that skip design entirely.
Compares
| vs | Pick Figma AI (Make / First Draft) when | Pick the other when |
|---|---|---|
| CanvaFull comparison → | Figma AI designs the product itself | the brand, marketing and everything around the product |
| v0Full comparison → | Figma Make produces prototypes for learning | the artefact should be the product's real code |
| LovableFull comparison → | Figma AI hands a real Figma file to the founder's eventual first designer to inherit, with the prototype's generated code available as their engineering starting point too | the MVP itself needs building before a design or engineering hire exists, sign-up, data and payments included |
| Bolt (StackBlitz)Full comparison → | what accumulates is Figma files a first designer will inherit rather than replace, so the exploring leaves an asset behind instead of being cleared away | the phase is early validation and throwaway prototypes, before a concept is proven enough to justify a production stack |
Product management
Figma Make gets a PM to a working prototype without booking design or engineering time. Describe the flow, or start from the team's existing designs, and it produces an interactive front-end prototype inside the tool the design team already lives in, ready for user feedback or a stakeholder walkthrough the same day and looking like your product because it reads your files. For PMs who need ideas clickable, inside the team's Figma, it is the direct route. It builds front-end prototypes rather than products: no real backend, database or auth, so anything that must persist data graduates to a full-stack tool, and a convincing prototype reads as near-finished software to stakeholders, which makes labelling it clearly part of the job.
Example tasks
- Turn a described user flow into a clickable prototype for feedback
- Convert an existing Figma design into an interactive front-end
- Explore two variants of a screen and test them side by side
- Hand a validated prototype to engineering as a concrete reference
- Draft screens for the spec without waiting on design capacity
Limits
It builds front-end prototypes by default, and persistence, login and secret storage arrive only once a Supabase backend is added to the file, which Figma documents as a deliberate step.
Compares
| vs | Pick Figma AI (Make / First Draft) when | Pick the other when |
|---|---|---|
| LovableFull comparison → | Figma Make stays inside the design environment and excels at fidelity to your designs | the backend should come with the product rather than be added to it |
| v0Full comparison → | Make suits designers and PMs working visually | engineering wants production React components out the other end |
| UizardFull comparison → | Figma AI hands a validated prototype to engineering as the concrete reference it builds from, and drafts the spec's screens without waiting on design capacity | the product conversation has stalled for want of something to point at, and the alternative is a spec every reader interprets differently |
| Bolt (StackBlitz)Full comparison → | the prototype is generated from the team's own files, so it looks like the product because it was built out of it rather than described to resemble it | validating a feature concept or standing up a lightweight internal tool before committing engineering resources |
Tasks
Design, UI & prototyping
Figma Make is the prototyping route with the least friction for design teams. It reads your actual files, tokens and components, so prototypes come out looking like your product rather than a generic reinterpretation, and everything happens inside the tool designers already work in, with generated code available as an engineering starting point. Teams for whom fidelity to existing designs is the requirement get the category's best answer. The limits are structural: no backend, data persistence or auth, so prototypes that must behave like products graduate to the full-stack builders, generated code needs engineering review before production use, and a polished prototype invites stakeholders to assume the product is nearly done, so set expectations explicitly.
Example tasks
- Turn a designed flow into an interactive prototype without leaving Figma
- Generate a first-draft screen from a prompt, on your design system
- Add real interactions to static frames for usability testing
- Produce front-end code as an engineering starting point
- Restyle a draft against the design system's tokens by prompt
Limits
A Make file has no backend until one is added, and Figma documents a Supabase integration supplying a Postgres database, login screens and secret storage when it is. Output code needs engineering review before production use.
Compares
| vs | Pick Figma AI (Make / First Draft) when | Pick the other when |
|---|---|---|
| v0Full comparison → | Make's access to real design metadata keeps prototypes faithful to your designs | the deliverable is production React components |
| UizardFull comparison → | Figma AI adds real interactions to static frames so they can be usability-tested, and restyles a draft against the design system's tokens by prompt | you are exploring what a product could look like, before design proper begins |
| LovableFull comparison → | Figma AI generates a first-draft screen from a prompt on your own design system and hands the resulting front-end code to engineering as a starting point, all without leaving Figma | the prototype has to work as well as look right, wired to a real backend, database and auth on a shareable URL |
| Base44Full comparison → | Figma AI (Make / First Draft) has no backend, no data persistence and no auth, so a prototype that must behave like a product graduates to a full-stack builder | you want the mockup to be a working, hosted app rather than a static design |
| Bolt (StackBlitz)Full comparison → | Figma AI (Make / First Draft) comes back polished enough that stakeholders assume the product is nearly done, which is an expectation to set explicitly rather than a compliment to accept | you want a fast full-stack prototype and intend to touch the code as well as the prompt |
Image editing
Figma's AI image tools cover the edits design work constantly needs
Figma's AI image tools cover the edits design work constantly needs. Background removal, upscaling of low-resolution assets and generated fill imagery run without leaving the canvas, which spares designers the round-trip to an editor for routine asset preparation and keeps the design file as the single working surface. Designers preparing assets inside Figma designs are the whole audience, and that boundary is the trade: these are canvas conveniences, so photographic retouching, compositing and darkroom work belong to the dedicated image software.
Example tasks
- Remove a background from an asset on the canvas
- Clean up placeholder imagery inside a design
- Generate quick image fills to test a layout
- Adjust an image to fit a frame without leaving Figma
- Replace stock placeholders with generated stand-ins
Limits
Its image tools are canvas conveniences: serious photo editing, compositing and retouching belong to dedicated image software. Expect cleanup and quick fixes, not darkroom work.
Compares
| vs | Pick Figma AI (Make / First Draft) when | Pick the other when |
|---|---|---|
| CanvaFull comparison → | Figma AI keeps routine image edits on the design canvas, removing backgrounds, upscaling low-resolution assets and generating fill imagery without leaving the file you are designing in | non-designers do the editing and the image is destined for a Canva design anyway |
| Flux (Black Forest Labs)Full comparison → | Figma AI (Make / First Draft) is for designers preparing assets inside Figma designs, and that is the whole audience | you are building image capability into a product or pipeline, or need generation fully in-house |
| KreaFull comparison → | Figma AI (Make / First Draft) spares the round-trip to an editor for routine asset preparation, which keeps the design file as the single working surface | editing is iterative and visual for you, and instant feedback beats parameter menus |
| Microsoft DesignerFull comparison → | Figma AI (Make / First Draft) generates quick image fills to test a layout and replaces stock placeholders with generated stand-ins, which is editing in service of a design in progress | the edit is routine, the budget is zero, and your work lives in Microsoft 365 |
Where to start
Not sure what to adopt first?
Five quick questions about your job, task and constraints. We'll suggest your top three tools, plus the one to try first.
Alternatives
Same category, different strengths.
Common questions
Is Figma AI (Make / First Draft) free?
There's a free tier to start; paid plans add capacity and features.
Where does Figma AI (Make / First Draft) fit best?
Figma AI (Make / First Draft) fits best in Design & creative and Founders & entrepreneurs; see its practice notes for how.
Before sharing confidential or personal data, check this tool's data-governance and training policies. They differ between providers and can change.
Last checked: August 2026