--- title: "AI Image Generator: Make Images from Text | imaginary.app" description: "Make images from a text prompt with 7 AI image models and one credit balance. See what each model does well and the cost before you start." url: https://www.imaginary.app/ai-image-generator --- Updated November 2026 # AI image generator imaginary.app makes still images from a text prompt with 7 image models, including FLUX Schnell, FLUX.2 Pro and Seedream 4.5. Pick a model, an aspect ratio and a resolution, see the credit cost, then generate. If a generation fails, its credits come back. Key takeaways - Image models available now: FLUX Schnell, FLUX.2 Pro, Seedream 4.5, Nano Banana 2, Nano Banana Pro, Ideogram 4.5 and Recraft V4.1. - Aspect ratios across these models: 16:9, 9:16, 1:1. Each model page lists its resolutions. - Images start at 0.07 credits ($0.01–$0.02) at the lowest settings; credit packs start at $9.99. - Image models need an account that has bought a credit pack or plan. Failed generations return their credits. Write a prompt and make your first image Choose an image model, pick a format, see the credit cost before you start, and get the credits back if a generation fails. [Open the generator](https://www.imaginary.app/generate)[View Pricing](https://www.imaginary.app/pricing) Sign in with Google to create an account; buy credits only when you need them. ## What you can make - **Product and marketing images.** Studio-style product shots, lifestyle scenes and backgrounds with room for your own copy. - **Posters, covers and graphics with text.** Some models render short headlines and labels far more reliably than others; the model pages say which. - **Concept art and illustration.** Characters, environments, mood boards and style explorations before you commit to a direction. - **Social images.** Square and vertical formats for posts and stories. - **Starting frames for video.** Generate a still, then animate it with [Veo 3.1 image-to-video](https://www.imaginary.app/models/veo-3-1/image-to-video). It is a good way to lock in a look before you spend credits on motion. ## How it works 1. ### Sign in and add credits Sign in with Google. The image models need an account that has bought a credit pack or plan; see [pricing](https://www.imaginary.app/pricing). 2. ### Write your prompt Describe the subject, the setting, the light, the composition and the style or medium. Put any words that should appear in the image in quotes. Prompts can be up to 2,000 characters. 3. ### Choose a model Pick the model that suits the job; the table below says what each is good at. 4. ### Set the format Choose the aspect ratio and resolution. Only the options the selected model supports are shown. 5. ### Check the cost and generate The generator shows the credit cost before you start. Credits are taken when the generation starts and returned automatically if it fails. 6. ### Download Finished images are saved to your account, where you can view and download them. ## Choose an image model Every image model you can use here right now. Starting prices are each model's lowest settings, from our live model catalog; the generator shows the exact cost for the settings you pick. | Model | Maker | Good at | Resolutions | Starting at | | ------------------------------------------------------------------- | ----------------- | ----------------------------------------------------- | ----------- | -------------------------------- | | [FLUX Schnell](https://www.imaginary.app/models/flux-schnell) | Black Forest Labs | Quick sketches, concepts and everyday images. | 1K | 0.07 credits (about $0.01–$0.02) | | [FLUX.2 Pro](https://www.imaginary.app/models/flux-2-pro) | Black Forest Labs | Photoreal detail and faithful prompt following. | 1K | 0.25 credits (about $0.05–$0.06) | | [Seedream 4.5](https://www.imaginary.app/models/seedream-4-5) | ByteDance | Detailed compositions and polished visual work. | 2K | 0.33 credits (about $0.07–$0.08) | | [Nano Banana 2](https://www.imaginary.app/models/nano-banana-2) | Google | Precise image generation in multiple resolutions. | 1K, 2K, 4K | 0.64 credits (about $0.14–$0.16) | | [Nano Banana Pro](https://www.imaginary.app/models/nano-banana-pro) | Google | Google’s most capable image model, with legible text. | 1K, 2K, 4K | 1.18 credits (about $0.25–$0.29) | | [Ideogram 4.5](https://www.imaginary.app/models/ideogram-4-5) | Ideogram | Posters, logos and images with accurate text. | 1K | 0.48 credits (about $0.10–$0.12) | | [Recraft V4.1](https://www.imaginary.app/models/recraft-v4-1) | Recraft | Design-ready brand and editorial images. | 1K | 0.29 credits (about $0.06–$0.07) | ### A quick way to pick - [FLUX Schnell](https://www.imaginary.app/models/flux-schnell) (Black Forest Labs): Brainstorming: trying ten framings of an idea before committing to one. - [FLUX.2 Pro](https://www.imaginary.app/models/flux-2-pro) (Black Forest Labs): Photoreal product shots, lifestyle scenes and editorial imagery meant for publication. - [Seedream 4.5](https://www.imaginary.app/models/seedream-4-5) (ByteDance): Posters, flyers and social graphics with a short headline and tagline. - [Nano Banana 2](https://www.imaginary.app/models/nano-banana-2) (Google): Everyday images that need to follow a detailed instruction closely without waiting on a heavier model. - [Nano Banana Pro](https://www.imaginary.app/models/nano-banana-pro) (Google): Infographics, explainers and labelled diagrams with real content. - [Ideogram 4.5](https://www.imaginary.app/models/ideogram-4-5) (Ideogram): Posters, flyers and event graphics with a headline and one or two short lines. - [Recraft V4.1](https://www.imaginary.app/models/recraft-v4-1) (Recraft): Brand illustration, editorial spot art and campaign key visuals. ## What to look for in an image model - **Text in the image.** If the picture must carry a headline, label or logo-style lettering, choose a model whose page says it renders text well, and keep the text short. - **Photo or style.** Some models lean towards photorealism, others towards illustration and design. Try the same prompt on two models before a big batch. - **Prompt following.** Long, specific prompts with several objects separate the models most. Count whether everything you asked for is there. - **Resolution and shape.** Check the resolutions in the table against where the image will be used, and pick the aspect ratio before you generate rather than cropping afterwards. A prompt that gives any model enough to work with: Example prompt (written by us) ``` Flat-lay product photo of a ceramic coffee mug on a pale oak table, soft morning window light from the left, a folded linen napkin and two coffee beans beside it, shallow depth of field, muted warm colours, plenty of empty space at the top for a headline. ``` ## What it costs You pay per image in credits. A credit costs $0.21 to $0.25 depending on the pack or plan you buy it with, and the smallest one-time pack is $9.99, with no subscription required. Higher resolutions can cost more on models that offer several. The same credits work for video, including Veo 3.1. ## If a generation fails Credits are taken when a generation starts. If the model provider rejects the request, the output fails the safety check or the generation fails for another reason, the credits go back to your balance automatically. You can also cancel before the request is submitted. Very rarely, when we can't confirm with the provider whether a generation finished, the credits stay reserved while we check, rather than being charged. ## Limits to know about - The image models here work from a text prompt only: no uploads, edits or reference images. - Image models have daily usage limits, per account and across the site. If one is reached, the generator tells you and you can try again the next day (limits reset at midnight UTC). - Image generation is in the web generator only; our developer API with `veo_` keys serves Veo 3.1 video. - Every model has its own limits on text, hands, faces and fine detail. Each model page lists the ones we know about. Want moving pictures instead? See the [AI video generator](https://www.imaginary.app/ai-video-generator) or every model on the [models hub](https://www.imaginary.app/models). ## Frequently asked questions ### Is this AI image generator free? Creating an account is free: you sign in with Google and no card is needed. Generating images uses credits, and the image models need an account that has bought a credit pack or plan. Packs start at $9.99. ### Which image model should I use? It depends on the job. The model table on this page lists what each one is good at, and each model page goes into strengths, limits and prompt tips. Today you can choose from FLUX Schnell, FLUX.2 Pro, Seedream 4.5, Nano Banana 2, Nano Banana Pro, Ideogram 4.5 and Recraft V4.1. ### Can I edit an uploaded photo? Not in our image generator today. The image models here create new images from a text prompt; there is no upload, edit or reference-image option. ### Can I turn a generated image into a video? Yes. Download the image, then upload it in the video generator as the starting frame for Veo 3.1 image-to-video and describe the motion you want. ### What happens if an image fails to generate? The credits for that generation go back to your balance automatically. You can also cancel a generation before it is submitted and get the credits back. ### Can I use the images commercially? Check our Terms of Service and the model maker’s licence before you rely on it. Each model page links to its maker’s documentation. ## Sources Prices, model specs and dates on this page were checked on November 10, 2026. Third-party prices change; check the source before you rely on a number. - [Black Forest Labs — FLUX.1 \[schnell\] model card (Hugging Face)](https://huggingface.co/black-forest-labs/FLUX.1-schnell) - [Black Forest Labs — FLUX.2 announcement (November 25, 2025)](https://bfl.ai/blog/flux-2) - [BytePlus (ByteDance) — Seedream 4.5 announcement, December 3, 2025](https://www.byteplus.com/en/blog/seedream4-5) - [Google blog — Nano Banana 2 announcement, February 26, 2026](https://blog.google/innovation-and-ai/technology/ai/nano-banana-2/) - [Google blog — Nano Banana Pro announcement, November 20, 2025](https://blog.google/technology/ai/nano-banana-pro/) - [Ideogram — Ideogram 4.5 model page](https://ideogram.ai/models/4.5/) - [Recraft — Recraft V4.1 model page](https://www.recraft.ai/docs/recraft-models/recraft-v4-1) - [imaginary.app pricing](https://www.imaginary.app/pricing) How we checked: model availability, settings and starting credits come from our live model catalog; model details come from each maker's documentation, linked on the model pages. ## Make your first AI image Sign in, write a prompt and pick a model. One-time packs from $9.99, the cost shown before you generate, and credits back on failures. [Open the generator](https://www.imaginary.app/generate)[View Pricing](https://www.imaginary.app/pricing) Sign in with Google to create an account; buy credits only when you need them.