Directory
AI image generator directory: 24 tools, free options marked
A neutral list of AI image generators: chat assistants, dedicated apps, design suites, model hubs and the labs behind the models, with the official link and free option for each.
- 24 tools
- A to Z, not a ranking
- Last updated:
Our picks
The short ranked list from our best-of page. The complete list is below.
- 1
Nano Banana (Google Gemini)The best overall free tier: quality, allowance, and editing
- 2
ChatGPT image generationFree images inside a tool you may already use
- 3Bing Image Creator / Microsoft Designer
The most frictionless free option
- 4Ideogram
Free images with readable text: posters, logos, memes
This is a catalogue, not a ranking. It lists the AI image generators we know about, grouped by what kind of product they are, with the official link and what each site says about free access.
Our recommendations live on separate pages. If you want a short list of picks, start with Best free AI image generators: what you get in 2026. Use this directory when you want to see what exists, or to check a name you keep running into.
Showing 24 of 24
Chat assistants that generate images
You describe the picture in a conversation and refine it by replying. Image generation is one feature of a larger assistant.
Bing Image Creator
In our picks, #3
A free image generator inside Bing. The page says guests get 10 fast-mode creations a day and unlimited standard-mode ones, with sign-in unlocking custom prompts and more advanced models. It lists two modes: a vivid, natural one (MAI-Image-2.5-Flash) and a stylized illustration one (MAI-Image-2e, login needed).
Free optionDetails →ChatGPT
In our picks, #2
OpenAI's assistant creates images from chat prompts. Its pricing page lists limited image creation on the Free plan, more on Go, and unlimited, faster image creation on Pro.
Free optionDetails →Google Gemini (Nano Banana)
In our picks, #1
Gemini generates and edits images with Google's Nano Banana models, including edits from reference images and text rendered inside the image. Google says it adds a visible watermark and an invisible SynthID mark, and lets you check an image by uploading it to Gemini. Image generation is listed in the free plan.
Free optionDetails →
Dedicated image generators
Products built around generating images, usually with controls for style, size and variations that a chat window does not offer.
Image tool built around mixing and editing: Splicer blends images and adjusts traits like age, and Collage builds an image from shapes, images and text. It also runs a community with contests and remix events. Its pricing page lists credit-based paid plans from $7.49 a month and does not state a free tier.
Pricing: see siteDetails →Text-to-image generator that its FAQ says is free to everyone, with limits on images and features for free users. It offers style choices such as photo, anime and vector, plus an exclude field. The FAQ says subscribers get faster access, better downloads and no watermark.
Free optionDetails →Browser text-to-image generator. Its page says no sign-up is needed for core features, while HD and higher-quality modes sit behind a Pro plan listed at $9.99 a month.
Free optionDetails →A workspace that offers several third-party image models alongside video, music, speech and sound effects, plus upscaling and background removal. Its pricing lists four paid credit tiers and mentions no free plan. Its FAQ says commercial use of generated images requires a paid plan.
Pricing: see siteDetails →Ideogram
In our picks, #4
Has a $0 plan that gives slow credits weekly to eligible accounts and allows one generation at a time. Private generations are listed only on paid plans (Plus, Pro, Team), so free-plan prompts should be treated as potentially public. Its models include Ideogram 4.5, 4.0 and 3.0.
Free optionDetails →A creative suite for generating, editing and upscaling images, video and 3D, and for training LoRA styles. The free plan lists 100 compute units per day and needs no credit card. Its pricing page says the paid plans (from $9 per month) include a commercial license.
Free optionDetails →
Leonardo AI
In our picks, #6
Image, video and design generation under one subscription. The free plan gives 150 fast tokens per day and keeps creations public. Paid plans start at $12 per month and add private creations, and its pricing page lists unlimited relaxed-pace generation on select models only from the $30 tier.
Free optionDetails →
Midjourney
In our picks, #7
Subscription only: its plan docs list Basic at $10, Standard at $30, Pro at $60 and Mega at $120 per month, with 20% off for annual billing, and no free tier. Private Stealth Mode needs Pro or Mega. Its terms say company use is allowed, but a company with over $1,000,000 in yearly gross revenue must be on Pro or Mega.
Paid onlyDetails →An AI art platform that offers many image models in one place. Its pricing page lists unlimited base Stable Diffusion creations and 5 free credits on daily login, plus 3 more for daily challenges, with extra free credits for streaks. Paid NightCafe PRO is billed monthly, quarterly or annually.
Free optionDetails →A design-focused image tool that lists editable vector generation, custom styles from reference images, and mockups. A free plan exists, but its pricing page says Free-plan images are owned by Recraft, publicly visible and not licensed for commercial use. Paid plans (Basic, Pro, Teams) give the user ownership and commercial rights.
Free optionDetails →
Design suites and editors with image generation
Editors and design tools where generation sits next to templates, layout and photo editing. Useful when the image is going straight into a design.
Adobe's generation product for images, vectors, video, audio and designs, with models from Adobe and partners. The Firefly Free plan gives limited daily generations. Adobe says its own Firefly models are trained on licensed Adobe Stock and public-domain content, and that it does not train on users' content.
Free optionDetails →Turns a text prompt or a reference photo into an image inside Canva, with a choice of style and aspect ratio. The page lists 10+ preset styles (such as Photo, Cinematic and Sketch) and related text-to-graphic and text-to-video tools. The page title calls it a free generator, but it gives no usage limits.
Free optionDetails →Text-to-image and image-to-image generation with several models (it lists Flux, GPT Image 2, Gemini and Nano Banana). The page says you can start without signing up and that free users get daily credits, without stating the number. Its FAQ says generated images are supported for commercial projects.
Free optionDetails →A browser photo editor that also generates images and video, and lists tools such as background removal, generative fill and upscaling. The site says its free version needs no account. Paid plans are Plus, Premium, Ultra and Ultra MAX, and its pricing page lists Plus at 1.99 euros per month on yearly billing with 80 monthly AI credits.
Free optionDetails →An AI design studio for logos, t-shirts, stickers, posters and social graphics, with templates and several image models. Its pricing page lists a free plan limited to 10 images every 3 hours, plus paid plans from $12 per month on annual billing. The page says you own what you create and may use it commercially.
Free optionDetails →
Communities and model hubs
Places to find models, share work and sometimes generate on site. Quality and rules vary by uploader, so these need more reading than a single-vendor product.
A community model and image hub for AI art, with galleries of images, models and videos, plus on-site generation paid in a currency it calls Buzz. Its pricing page lists Bronze, Silver and Gold memberships at $10, $25 and $50 per month. Content settings control what adult-oriented material you see.
Pricing: see siteDetails →The Hugging Face model hub filtered to text-to-image. Its pricing page says the Hub is free to use, with a PRO account at $9 per month. Each model carries its own license, so check it before using output commercially.
Free optionDetails →A community and creation platform for images, video and characters, with web, iOS and Android apps. It lists tools such as upscaling, background removal and face swap, and says it integrates models including Veo and Kling. The homepage mentions free core tools but gives no credit amounts or prices.
Pricing: see siteDetails →
The labs that make the models
Organisations that train image models. You may meet their models inside other tools on this page, or use them directly through an API or your own hardware.
The lab behind the FLUX models, with FLUX 3 Image for generation and a video model. It offers a pay-as-you-go API, and its pricing page lists FLUX 3 Image at $0.048 per image. Open weights are licensed in tiers (Builder, Platform, Professional, Enterprise), with image-per-month caps on the lower tiers. The site also has a free browser playground.
Pricing: see siteDetails →Alibaba's Qwen model family. Its Qwen-Image model (20 billion parameters, released August 2025) does text-to-image and image editing, with a focus on text rendering, and its Hugging Face page names the Apache 2.0 license for that model. See our Qwen Image 3 page for what we have recorded about the newer one.
Pricing: see siteDetails →The company behind Stable Diffusion, now selling models, a platform API and enterprise tools across image, video, audio and 3D. Its Community License lets individuals and organizations under $1M annual revenue use the core models free, including commercially. Larger organizations need an Enterprise License. The license says you own the outputs.
Free optionDetails →
How this directory works
Entries are alphabetical inside each group. Position carries no meaning, and a tool being listed is not a recommendation.
We include a tool when it has a public image generator and an official site we could open. Each entry shows the date its facts were last read from the tool's own site, or from our own pages where we already track it. Where a site did not state its pricing, the entry says to check the site instead of guessing.
A free option here means the tool's own site describes one. It does not tell you how good the free output is, which is a separate question that our ranked pages try to answer.
Choosing between the groups
Chat assistants suit people who already use one and want an occasional image. Dedicated generators suit repeated work, where style controls and batch options matter. Design suites suit images that end up in a post, a slide or a product page.
Hubs and model makers are the most hands-on groups. They are where open models appear first, and where licences differ most from one model to the next.
Check before you rely on a free tier
Plans, caps and models change without notice, which is why every entry carries a date. Before using output commercially, read the tool's current terms for watermark rules, public-gallery rules and commercial use. They differ between tools and between a free plan and a paid one.
Missing a tool or spotted a mistake? Tell us.
Frequently asked questions
- Is this list ranked from best to worst?
- No. Entries are alphabetical inside each group, and the directory makes no quality judgement. Our ranked picks are on the best-of pages, which are written separately.
- Has anyone paid to be listed here?
- No. Listings are not paid, and the links are plain outbound links marked nofollow. If sponsored placements are ever added, they will be labelled as sponsored and will not change the order of editorial entries.
- How current is the free-tier information?
- Each entry shows the date its facts were last read from the source. Free plans change often, so treat the date as the limit of what we know and confirm on the tool's own site before signing up.
- Why are some tools marked 'see site' for free access?
- The tool's site did not state its free access in a way we could record. We would rather say so than guess.
- How can a tool be added or corrected?
- Use the contact page. Send the official URL and what the tool does, and we will check the facts on its own site before adding or changing an entry.
Get new guides by email
One email when we publish new guides and model breakdowns. No spam, unsubscribe anytime.