AI Image Generator

AI Image Generator

Do it with the Agent

Model

Reference images (optional)0/8

Drop, paste or click to add. JPG, PNG or WebP up to 10 MB.

0/20000

Aspect ratio
Resolution

Your images appear here

Pick a model, describe what you want and press Generate. Add reference images to edit or restyle a picture.

History

Your generated images will show up here.

The AgentReel AI image generator creates and edits pictures from a text prompt, with models such as Nano Banana Pro, GPT Image 2.5 and Seedream 5.0. Add reference images to edit, restyle or combine pictures. For a ready-made look on your own photo, the one-click photo filters below, such as golden hour, CCD camera or film halation, open an edit model with the prompt already written. Z-Image works on a free account; every other model uses purchased credits.

Last updated

One-click filter presets

Each preset opens the generator with Nano Banana 2.1 selected (1–3 credits per photo, depending on resolution) and the prompt below already filled in. Pick a look first, then upload your photo and press Generate. You can edit the prompt before you run it, or switch to another model.

  • Golden hour

    Re-light this photo as if shot at golden hour: low warm sun from the side, long soft shadows, honey-colored highlights on skin and hair. Keep the person, pose, clothes and framing exactly the same.

    Use this preset
  • Blue hour

    Turn this photo into a blue hour scene: deep cool blue sky just after sunset, soft even light on the subject, warm city lights glowing in the background. Keep faces, pose and composition unchanged.

    Use this preset
  • CCD camera

    Make this photo look like it was taken on a 2005 compact CCD digital camera: direct on-camera flash, slightly cool colors, crisp digital noise, a little overexposed highlights. Keep the subject and framing the same.

    Use this preset
  • Old phone camera

    Restyle this photo as an early smartphone snapshot: soft detail, muted colors, slight JPEG compression, flat lighting and a faint warm cast. Do not change the people or the scene.

    Use this preset
  • Film halation

    Give this photo a cinematic film look with halation: red-orange glow around bright edges and light sources, gentle grain, lifted blacks and rich color. Keep the subject, pose and background identical.

    Use this preset
  • Rim light

    Add a strong rim light behind the subject so a bright thin outline separates hair and shoulders from a darker background. Keep the face lit softly from the front and leave pose and framing unchanged.

    Use this preset
  • Butterfly lighting

    Re-light this portrait with butterfly lighting: a soft key light high and centered in front of the face, a small shadow under the nose, glowing cheekbones, clean beauty-studio look. Keep the face and expression the same.

    Use this preset
  • Pink sunset

    Recolor this photo with a pink sunset sky: pastel pink and lilac clouds, warm pink light falling on the subject, soft dreamy contrast. Keep people, pose and composition exactly as they are.

    Use this preset
  • Warm film

    Grade this photo like warm 35mm film: amber midtones, creamy highlights, soft grain and slightly faded shadows. Keep the subject, outfit and framing unchanged.

    Use this preset
  • Lo-fi dusk

    Turn this photo into a lo-fi dusk mood: dim violet evening light, soft blur, low contrast, a few warm street lamps and a quiet nostalgic feel. Keep the person and pose the same.

    Use this preset
  • Cobalt blue

    Apply a bold cobalt blue color grade: deep saturated blues in shadows and background, skin tones kept natural, high-contrast editorial look. Keep the composition and subject unchanged.

    Use this preset
  • Water reflection

    Add a calm water surface at the bottom of the frame that mirrors the subject and the sky, with gentle ripples and soft light. Keep the subject, pose and upper half of the photo the same.

    Use this preset

Models that can apply a filter to your photo

A filter needs a model that accepts an uploaded photo. 21 models in the generator do. The price below is for one photo in, read from the live price list; it changes with the resolution or quality you pick and shows on the Generate button before you start.

ModelVendorMax reference imagesCredits per photo
Nano Banana ProGoogle85–6
Nano Banana 2.1Google101–3
Nano Banana 2Google102–5
Nano Banana 2 LiteGoogle101
Nano BananaGoogle101
GPT Image 2.5 SunburstOpenAI162–4
GPT Image 2.5 FlareOpenAI162–4
GPT Image 2OpenAI162–4
GPT Image 1.5OpenAI161–6
Seedream 5.5ByteDance102
Seedream 5.0 ProByteDance102–4
Seedream 5.0 LiteByteDance142
Seedream 5.0 FlashByteDance101
Seedream 4.5ByteDance142
FLUX 3 KleinBlack Forest Labs101–2
Flux 2 ProBlack Forest Labs82
Flux KontextBlack Forest Labs12–3
Ideogram V3Ideogram11–3
Qwen Image 3.0 ProAlibaba32–3
Grok Imagine Image 2.0xAI51
Wan 2.7 Image ProAlibaba93

How the AI image generator works

  1. 1

    Choose a model

    Compare models by price and abilities. Some only create from text; others also edit the images you upload.

  2. 2

    Write a prompt

    Describe the subject, style, lighting and mood. Add reference images to keep a face, a product or a layout.

  3. 3

    Generate and download

    Set the aspect ratio and quality, press Generate and download the full-resolution result.

AI image models you can use

23 models from Google, OpenAI, ByteDance, Black Forest Labs, Alibaba, Ideogram, xAI. Prices are in credits per image.

  • Nano Banana Pro

    Pro

    Google

    5–6 credits · Edit · up to 8 images

  • Nano Banana 2.1

    New

    Google

    1–3 credits · Edit · up to 10 images

  • Nano Banana 2

    Google

    2–5 credits · Edit · up to 10 images

  • Nano Banana 2 Lite

    New

    Google

    1 credit · Edit · up to 10 images

  • Nano Banana

    Fast

    Google

    1 credit · Edit · up to 10 images

  • GPT Image 2.5 Sunburst

    New

    OpenAI

    2–4 credits · Edit · up to 16 images

  • GPT Image 2.5 Flare

    New

    OpenAI

    2–4 credits · Edit · up to 16 images

  • GPT Image 2

    OpenAI

    2–4 credits · Edit · up to 16 images

  • GPT Image 1.5

    OpenAI

    1–6 credits · Edit · up to 16 images

  • Seedream 5.5

    New

    ByteDance

    1–2 credits · Edit · up to 10 images

  • Seedream 5.0 Pro

    Hot

    ByteDance

    2–4 credits · Edit · up to 10 images

  • Seedream 5.0 Lite

    ByteDance

    2 credits · Edit · up to 14 images

  • Seedream 5.0 Flash

    Fast

    ByteDance

    1 credit · Edit · up to 10 images

  • Seedream 4.5

    ByteDance

    2 credits · Edit · up to 14 images

  • FLUX 3 Klein

    New

    Black Forest Labs

    1–2 credits · Edit · up to 10 images

  • Flux 2 Pro

    Black Forest Labs

    2 credits · Edit · up to 8 images

  • Z-Image

    Fast

    Alibaba

    3 credits · Text only

  • Flux Kontext

    Black Forest Labs

    2–3 credits · Edit · up to 1 image

  • Ideogram V3

    Ideogram

    1–3 credits · Edit · up to 1 image

  • Qwen Image 3.0 Pro

    Alibaba

    2–3 credits · Edit · up to 3 images

  • Grok Imagine Image 2.0

    xAI

    1 credit · Edit · up to 5 images

  • Wan 2.7 Image Pro

    Alibaba

    3 credits · Edit · up to 9 images

  • Imagen 4

    Google

    1–3 credits · Text only

Every image model side by side: credits per image (lowest to highest setting), reference images and maximum resolution.
ModelVendorCredits per imageReference imagesMaximum resolution
Nano Banana ProGoogle5–6Edit · up to 8 images4K
Nano Banana 2.1Google1–3Edit · up to 10 images4K
Nano Banana 2Google2–5Edit · up to 10 images4K
Nano Banana 2 LiteGoogle1Edit · up to 10 images–
Nano BananaGoogle1Edit · up to 10 images–
GPT Image 2.5 SunburstOpenAI2–4Edit · up to 16 images4K
GPT Image 2.5 FlareOpenAI2–4Edit · up to 16 images4K
GPT Image 2OpenAI2–4Edit · up to 16 images4K
GPT Image 1.5OpenAI1–6Edit · up to 16 images–
Seedream 5.5ByteDance1–2Edit · up to 10 images2K
Seedream 5.0 ProByteDance2–4Edit · up to 10 images2K
Seedream 5.0 LiteByteDance2Edit · up to 14 images4K
Seedream 5.0 FlashByteDance1Edit · up to 10 images2K
Seedream 4.5ByteDance2Edit · up to 14 images4K
FLUX 3 KleinBlack Forest Labs1–2Edit · up to 10 images4K
Flux 2 ProBlack Forest Labs2Edit · up to 8 images2K
Z-ImageAlibaba3Text only–
Flux KontextBlack Forest Labs2–3Edit · up to 1 image–
Ideogram V3Ideogram1–3Edit · up to 1 image–
Qwen Image 3.0 ProAlibaba2–3Edit · up to 3 images2K
Grok Imagine Image 2.0xAI1Edit · up to 5 images–
Wan 2.7 Image ProAlibaba3Edit · up to 9 images2K
Imagen 4Google1–3Text only–

How to Choose a Model in the AI Image Generator

Free and Paid: What the AI Image Generator Costs

Every picture in this AI image generator has a price in credits, and the exact number appears on the Generate button before you start. Most images cost between 1 and 6 credits, depending on the model and the resolution or quality you pick. If the model cannot produce an image, the credits return to your balance automatically, so a failed attempt costs nothing.

Z-Image is the free-plan model. It costs a fixed 3 credits per picture, and a free account can use it with no daily limit, paid from welcome credits and the daily check-in. The check-in adds 15 credits a day, enough for five Z-Image pictures. Guests can try the AI image generator without an account: pressing Generate starts a free guest session, and a new guest's welcome credits pay for a Z-Image after a short queue.

Every other model in the AI image generator needs purchased credits. Buying a pack removes the queue and unlocks all 23 models; the packs are listed on the pricing page. Paid pictures are often cheaper than you might expect: Nano Banana, Nano Banana 2 Lite, Nano Banana 2.1 at 1K, Seedream 5.0 Flash, Grok Imagine Image 2.0 and Imagen 4 Fast each cost 1 credit per image.

Text-to-Image or Editing With Reference Images

The AI image generator works in two modes. With a prompt alone, the model creates a new picture from scratch. Add one or more reference images and most models switch to editing: they keep a face, a product or a layout from your upload and change what you describe, such as the background, the outfit, the season or the art style. Models that accept references carry an Edit label on their card, together with the number of images they take.

The limits differ a lot between models. The GPT Image models accept up to 16 reference images, Seedream 5.0 Lite and Seedream 4.5 take up to 14, the Nano Banana 2 family takes up to 10, and Wan 2.7 Image Pro takes up to 9. Flux Kontext and Ideogram V3 work from a single image. Z-Image and Imagen 4 are text only, so they take no uploads and suit pure creation from a prompt. If your source is a single photo, any model with an Edit label will do; the high limits matter only when you mix several sources in one picture.

References can be JPG, PNG or WebP files up to 10 MB, and you can upload them, drag them in or paste them. Several references let the AI image generator combine sources: put a product into a new scene, dress a character in a garment from another photo, or merge a logo into a mockup. To cut a subject out before you use it as a reference, run it through the free background remover first.

Resolution, Aspect Ratio and Quality Settings

Resolution in the AI image generator comes as named steps rather than pixel sizes. The Nano Banana 2 family and the GPT Image 2 family offer 1K, 2K and 4K. Seedream 5.0 Lite renders 2K, 3K or 4K for the same 2 credits, and Seedream 4.5 renders 2K or 4K for 2 credits as well. Flux 2 Pro, Qwen Image 3.0 Pro and Wan 2.7 Image Pro stop at 2K. Other models trade a quality or speed setting instead: GPT Image 1.5 has Medium and High, Ideogram V3 has Turbo, Balanced and Quality, and Imagen 4 has Fast, Standard and Ultra.

Aspect ratio decides where the picture can go. Use 1:1 for profile images and feeds, 4:5 or 3:4 for portrait posts, 9:16 for stories and phone wallpapers, and 16:9 or 21:9 for banners and slides. Nano Banana 2.1 and Nano Banana 2 add extreme strips of 1:4, 4:1, 1:8 and 8:1, and GPT Image 2 adds 2:1 and 1:2. Several models also offer Auto, which follows the shape of your reference image. Pick the ratio before you generate rather than cropping later, because cutting a finished square down to a wide banner throws away most of the picture and the detail you paid for.

A sensible workflow is to draft at 1K or on a fast model and keep the higher setting for the final version. If a picture comes out right but too small for print, enlarge it with the free image upscaler instead of paying the AI image generator for a full new render.

Google and OpenAI Models: Nano Banana, Imagen and GPT Image

Nano Banana Pro from Google is the default model of the AI image generator and carries the Pro badge. It costs 5 credits at 1K or 2K and 6 credits at 4K, takes up to 8 reference images, and accepts prompts up to 20,000 characters. Nano Banana 2.1, marked New, costs 1 to 3 credits from 1K to 4K, and Nano Banana 2 costs 2 to 5. The original Nano Banana, marked Fast, costs 1 credit per image with up to 10 references and no resolution choice, which makes it a quick model for drafts and edits.

Imagen 4, also from Google, is a text-only model in three versions: Fast for 1 credit, Standard for 2 and Ultra for 3. Choose it when you want a clean new picture from a prompt and have nothing to upload. Imagen 4 accepts prompts up to 5,000 characters in five ratios: 1:1, 16:9, 9:16, 3:4 and 4:3. Fast is handy for testing a composition in the AI image generator, and Ultra is the step to take once the prompt is settled.

OpenAI's GPT Image line is the best option in this AI image generator when an edit needs many inputs, because every model in it accepts up to 16 reference images. GPT Image 2.5 Sunburst and GPT Image 2.5 Flare, both marked New, and GPT Image 2 each cost 2, 3 or 4 credits at 1K, 2K or 4K. GPT Image 1.5 costs 1 credit at Medium quality and 6 at High, in square, 2:3 or 3:2 formats.

Seedream, Flux, Qwen, Wan, Ideogram and Grok in the AI Image Generator

ByteDance's Seedream family covers every budget. The new Seedream 5.5, marked New, costs 1 credit at 1K or 1.5K and 2 at 2K, takes up to 10 references, and each reference adds a little to the price. Seedream 5.0 Pro, marked Hot, costs 2 credits at 1K and 4 at 2K, and the price rises slightly when you add more than one reference image. Seedream 5.0 Lite costs 2 credits at any of its 2K, 3K or 4K sizes, Seedream 5.0 Flash, marked Fast, costs 1 credit, and Seedream 4.5 costs 2 credits at 2K or 4K. Lite and 4.5 accept up to 14 references, which helps when a whole set of product photos must stay consistent.

Black Forest Labs offers Flux 2 Pro for 2 credits at 1K or 2K with up to 8 references, and Flux Kontext in Pro (2 credits) and Max (3 credits) for single-image edits. Kontext works in English, so prompts in other languages are translated to English before they reach it. Qwen Image 3.0 Pro from Alibaba costs 2 or 3 credits with up to 3 references, and Wan 2.7 Image Pro costs 3 credits with up to 9.

Ideogram V3 trades speed for detail across three rendering speeds: Turbo for 1 credit, Balanced for 2 and Quality for 3, from text or one reference image. Grok Imagine Image 2.0 from xAI costs 1 credit and takes up to 5 references. Z-Image from Alibaba, the free-plan model, rounds out the list at 3 credits with a 1,000-character prompt limit.

Prompt Craft for Better Pictures

A strong prompt for an AI image generator describes a picture, not a topic. Start with the subject, then the setting, then the style, the light and the camera. Compare a coffee shop with a small corner coffee shop at dawn, steam rising from a ceramic cup on a wooden counter, soft window light, shot on 35mm film, shallow depth of field. The second prompt gives the model decisions it would otherwise make at random. Name colors, materials and textures too, because words like brushed steel, linen or matte paper give the AI image generator something concrete to render.

For edits, describe the change and say what must stay the same: keep the face and the pose, replace the background with a sunny beach, match the lighting. When you combine several references, say which image supplies what, for example the product from the first image and the room from the second. Keep prompts within the model's limit: Z-Image accepts 1,000 characters, Seedream 4.5 and Seedream 5.0 Lite about 3,000, and the Nano Banana and GPT Image models 20,000. For ready-made looks on your own photo, such as golden hour, a CCD camera or film halation, the one-click photo filters on this page open an edit model with the prompt already written.

Test on a cheap model, change one thing at a time, and switch to a premium model once the idea works. Every result stays in your history, and the Use as reference button sends a finished picture straight back into the reference slot, so you can refine it step by step in the AI image generator instead of starting over from text. When the picture is final, you can bring it to life in the AI video generator as the start frame of a clip, so the same AI image generator session can feed a whole campaign of stills and short videos.

AI Photo Filters: Re-Light a Photo Instead of Tinting It

A classic photo filter is a color lookup: it shifts the existing pixels toward warmer, cooler or more faded values. It cannot add light that was never there, so a selfie taken under an office ceiling stays flat, only tinted. An edit model in the AI image generator reads the whole picture and draws a new version of it, so an AI photo filter can change the direction of the light, add a glow around a window or put a sunset behind a person.

The one-click photo filters on this page turn that into a single click. Each preset, from golden hour and blue hour to CCD camera, film halation and water reflection, opens the generator with an edit model selected and the prompt already written. Upload your photo, read the prompt, change any word you like or switch to another edit model, then press Generate.

The trade-off is control. Because the model repaints the image, small details can drift: a necklace may change, or text on a shirt may blur. A good prompt limits that drift by saying exactly what must stay the same, and every preset ends with such a keep line, naming the person, the face, the pose or the framing.

Use an AI photo filter wherever one consistent look matters more than a new picture: a profile photo with warmer light, one color mood across a feed, a product shot moved from flat studio light to a sunset, or an old-camera look for a nostalgia post.

Write Your Own Photo Filter Prompt

Describe the look in three parts: the light (direction, warmth, hardness), the color grade (which tones go warm or cool, how saturated) and the texture (grain, sharpness, compression). Then add a keep line: keep the face, pose, outfit and framing unchanged. For example: soft window light from the left, muted teal shadows with warm skin, fine film grain; keep the person and background the same.

Change one thing per run. If golden hour came out too orange, rerun with less saturated, soft gold light rather than rewriting the whole prompt. Every version stays in your history, and Use as reference sends a result back in as the next input, so you can stack small corrections instead of starting over.

For a set of photos, keep the prompt and the model the same and run each photo in turn. The results share a similar mood, so a photo series, a product line or a run of feed posts looks like one shoot. Each photo is a separate edit and is charged on its own.

Choose the Edit Model and Prepare the Photo

For quick looks on everyday photos, start with Nano Banana 2.1, the model every preset opens with. It is one of the cheapest edit models, so it suits trying several looks; its details are on the Nano Banana 2.1 model page. For close portraits where skin texture and the exact face matter most, try a premium model such as Nano Banana Pro, which costs more per photo.

If a filter must combine several inputs, for example your photo plus a color reference or a background plate, pick a model with more reference slots. The GPT Image family takes up to 16 reference images; see GPT Image 2.5 Sunburst. The table in the photo filter section lists every edit model with its reference limit and the credits for one photo, read from the live price list.

Filters are edits, so they need purchased credits. Z-Image, the model a free account can use, makes new pictures from text only and takes no uploaded photo, so a free account cannot filter its own photo. Upload a JPG, PNG or WebP image of up to 10 MB; if an edit fails, its credits return to your balance automatically.

Start from the best source you have. A blurry or noisy photo gives the model less to keep, so run it through the free photo enhancer first. After filtering, a result that looks right but is too small for print can go through the free image upscaler instead of a second paid run, and a filtered still can become the first frame of a clip in the AI video generator, with the same light and color.

AI image generator FAQ

Is the AI image generator free?
Partly. A free account can use Z-Image with no daily limit. Each Z-Image costs 3 credits, paid from your welcome or daily check-in credits. Every other image model needs purchased credits, and so do AI video models. Each image costs credits depending on the model and quality you choose; the price is shown on the Generate button before you start.
Do I need an account?
You can set up your image without one. When you click Generate we start a free guest session, and a new guest's welcome credits pay for a Z-Image after a short queue. If no credits are available, we ask you to sign in and claim the daily check-in (a verified email is needed). A free account can use Z-Image, video templates and Code to Video. Buying credits removes the queue and unlocks every model.
Can I edit my own photos?
Yes. Models marked with Edit accept reference images. Upload, drag in or paste a JPG, PNG or WebP image up to 10 MB, then describe the change you want. The one-click photo filters on this page start such an edit with the model selected and the prompt already written.
What happens if a generation fails?
If the model cannot produce an image, the credits for that image are refunded to your balance automatically.
Can I use the images commercially?
You can use the images you create, subject to our terms of service and the usage policy of the model you chose. Do not create content that infringes the rights of others.
Which AI image model should I choose?
For a flagship result, start with Nano Banana Pro, the default model with the Pro badge, or one of the new GPT Image 2.5 models. For cheap drafts, use Nano Banana, Seedream 5.0 Flash or Grok Imagine Image 2.0 at 1 credit each. For edits that combine many photos, use a GPT Image model (up to 16 reference images) or Seedream 5.0 Lite (up to 14). On a free account, Z-Image is the model you can use.
Which models can create 4K images?
Nano Banana Pro, Nano Banana 2.1, Nano Banana 2, GPT Image 2.5 Sunburst, GPT Image 2.5 Flare and GPT Image 2 offer a 4K setting, and Seedream 5.0 Lite and Seedream 4.5 render 4K for 2 credits. The price for every setting appears on the Generate button.
Can I edit my own photos on the free plan?
No. Z-Image, the model a free account can use, creates images from text only and takes no reference images. Editing with reference images needs purchased credits, and most edit-capable models cost between 1 and 6 credits per image. The one-click photo filters are edits too, so they also need purchased credits.
Will an AI photo filter change my face?
Small details can change, because an edit model redraws the whole picture. Every one-click photo filter ends with a line that tells the model what to keep, such as the person, the face or the framing, and you can add the same keep line to your own prompt. For close portraits, try a premium edit model such as Nano Banana Pro, which costs more per photo, and compare the result with the original.
Can I apply the same photo filter to many photos?
Yes. Keep the prompt and the model the same and run each photo in turn, and the set keeps a similar mood. Each photo is a separate edit and is charged on its own, at the price shown on the Generate button.