# Whisk AI Image Remixer: Blend a Subject, Scene and Style

> Whisk AI turns three pictures into one: drop in a subject, a scene and a style, add a few words if you like, and get a brand-new image from Nano Banana or GPT Image. Then animate it into a short video.

Remix studio: https://whiskai.net/image · Animate: https://whiskai.net/video · Pricing: https://whiskai.net/pricing · Gallery: https://whiskai.net/gallery

WhiskAI is an independent service. It is not affiliated with, endorsed or sponsored by Google; Whisk and Google are trademarks of Google LLC.

## What is Whisk AI?

Whisk AI (WhiskAI on whiskai.net) is a browser-based image remixer. You drop up to three pictures into labelled Subject, Scene and Style slots, add an optional prompt, and Nano Banana or GPT Image blends them into one new image. Any result can be animated into a short video with Seedance, Veo 3.1, Kling 4 or Grok Imagine.

One credit balance pays for every model. You see the exact cost before you generate, and failed renders are refunded automatically. WhiskAI is an independent service, not affiliated with, endorsed or sponsored by Google; Whisk and Google are trademarks of Google LLC.

## How Whisk AI works: subject, scene, style

Each slot tells the model what to take from that picture. Fill one, two or all three; the prompt is optional.

- **Subject** — The character, pet, product or object you want to keep. Whisk AI holds on to its identity, shape and key details. Works well: a clear photo of one thing, a mascot sketch, a product on a plain background.
- **Scene** — Where the subject should end up: a room, a street, a landscape or a layout. The scene sets background and composition. Works well: a travel photo, an interior, a shop shelf, a poster layout.
- **Style** — How the result should look: medium, palette, texture and lighting. Only the look is used, not the content of the style image. Works well: a watercolor, a clay render, a risograph print, a sticker sheet.
- **One new image** — Whisk AI sends the slots in order to Nano Banana or GPT Image with a short role note, plus your prompt. You get a fresh picture, not a collage.

No images? Whisk AI also works as a plain text-to-image generator: leave the slots empty and describe the picture.

## Remix in 3 steps with Whisk AI

1. **Drop your pictures** — Add a subject, a scene and a style image (any of them, all optional). JPG, PNG or WebP up to 10 MB each.
2. **Add a twist and pick a model** — Type a short instruction such as "as an enamel pin" or leave it blank. Choose Nano Banana Pro for fidelity or GPT Image for bold graphic looks, then the size and ratio.
3. **Remix, download, animate** — Most remixes finish in under a minute. Download the image, reuse the settings for a variation, or press Animate this to turn it into a video.

## Whisk AI style ideas: stickers, figurines, plush, posters

Popular looks for a Whisk AI remix, each with a prompt formula you can paste. Swap the words in brackets for your own subject.

- **Die-cut sticker** — Bold outline, white border, flat shading. Great for laptop stickers and chat packs. `[subject] as a glossy die-cut sticker, thick white border, bold outline, flat colors, centered on a plain background`
- **Plush toy** — Soft fabric, stitched seams and rounded proportions turn any character into a cuddly toy. `[subject] as a soft plush toy, felt and minky fabric, visible stitching, rounded proportions, studio photo on a pastel shelf`
- **Enamel pin** — Metal outlines, glossy enamel fills and a backing card read instantly as merch. `[subject] as a hard enamel pin, gold metal outlines, glossy color fills, on a kraft paper backing card, macro product photo`
- **3D figurine** — A collectible vinyl figure on a stand, with soft studio light and a toy-box feel. `[subject] as a collectible vinyl figurine on a round base, smooth matte plastic, soft studio lighting, toy packaging in the background`
- **Clay look** — Hand-made plasticine texture with thumbprints and warm light, like a stop-motion set. `[subject] sculpted from plasticine clay, visible fingerprints, handmade texture, warm soft light, miniature stop-motion set`
- **Poster** — Big type, strong shapes and a limited palette for gig posters and event flyers. `[subject] on a bold screen-printed poster, limited 3-color palette, large headline "[TEXT]", grain texture, centered layout`
- **Watercolor** — Loose washes, paper grain and soft edges for storybook and greeting-card looks. `[subject] in a loose watercolor illustration, soft washes, visible paper grain, gentle bleeding edges, white margins`
- **Product shot** — Put your product in a new scene with clean commercial lighting for listings and ads. `[product] placed in [scene], clean commercial lighting, soft shadow, shallow depth of field, e-commerce hero image`

## Nano Banana in Whisk AI: faithful multi-image remixes

Google’s Nano Banana family is the default Whisk AI engine. It reads several reference images at once, keeps a subject recognisable and places it convincingly into a new scene. Nano Banana Pro adds studio lighting, sharp text and 4K output.

## GPT Image in Whisk AI: bold graphic remixes

OpenAI’s GPT Image models follow long instructions and love graphic styles: posters, stickers, packaging and layouts with lots of text. Use them when the style slot matters more than photo realism.

- **Nano Banana Pro** — Google’s flagship — sharp text, studio lighting and up to 4K. 1K / 2K / 4K, up to 8 reference images.
- **Nano Banana 2.1** — Fast, faithful edits and character consistency at a low price. 1K / 2K / 4K, up to 8 reference images.
- **Nano Banana 2** — Detailed renders with wide aspect ratios and 4K output. 1K / 2K / 4K, up to 8 reference images.
- **Nano Banana 2 Lite** — The quickest Nano Banana for drafts and variations. 1K, up to 8 reference images.
- **Nano Banana** — The original Gemini image model — great for edits. 1K, up to 8 reference images.
- **GPT Image 2.5 Flare** — OpenAI’s newest — vivid, stylized images with crisp typography. 1K / 2K / 4K, up to 8 reference images.
- **GPT Image 2.5 Sunburst** — Warm, photographic GPT Image 2.5 tuned for realism. 1K / 2K / 4K, up to 8 reference images.
- **GPT Image 2** — Reliable layouts, posters and product shots up to 4K. 1K / 2K / 4K, up to 8 reference images.
- **GPT Image 2.6 Economy** — Low-cost GPT Image 2.6 for quick text-to-image ideas. 1K, up to 0 reference images.
- **GPT Image 1.5** — Medium or high quality GPT Image with strong prompt following. 1K / 2K, up to 16 reference images.
- **GPT Image 1 (4o)** — The classic GPT-4o image model — friendly, illustrative results. 1K, up to 5 reference images.

## Animate a Whisk AI remix into video

Every finished image has an Animate this button. It opens the video studio with your remix as the first frame, so you only describe the motion: a slow camera push, a wave, a turn of the head.

- **Veo 3.1 Fast** — Google’s cinematic model with native audio — fast renders up to 4K. 4–8s, 720p / 1080p / 4K, aspect ratios 16:9, 9:16.
- **Veo 3.1 Quality** — Highest-fidelity Veo 3.1 for hero shots, with dialogue and sound. 4–8s, 720p / 1080p / 4K, aspect ratios 16:9, 9:16.
- **Veo 3.1 Lite** — The most affordable Veo 3.1 — great for drafts and social clips. 4–8s, 720p / 1080p / 4K, aspect ratios 16:9, 9:16.
- **Seedance 2.5** — ByteDance’s newest — up to 30s, 30 reference images and 4K. 4–30s, 480p / 720p / 1080p / 4K, aspect ratios 16:9, 9:16, 1:1, 4:3, 3:4, 21:9.
- **Seedance 2.5 Flash** — Faster, cheaper Seedance 2.5 at 480p or 720p. 4–30s, 480p / 720p, aspect ratios 16:9, 9:16, 1:1, 4:3, 3:4, 21:9.
- **Seedance 2.0** — Multi-shot storytelling with native audio, up to 15s and 4K. 4–15s, 480p / 720p / 1080p / 4K, aspect ratios 16:9, 9:16, 1:1, 4:3, 3:4, 21:9.
- **Seedance 2.0 Fast** — Quicker Seedance 2.0 renders at 480p or 720p. 4–15s, 480p / 720p, aspect ratios 16:9, 9:16, 1:1, 4:3, 3:4, 21:9.
- **Seedance 2.0 Mini** — The lowest-cost Seedance model — ideal for testing ideas. 4–15s, 480p / 720p, aspect ratios 16:9, 9:16, 1:1, 4:3, 3:4, 21:9.
- **Kling 4.0** — Up to 30s with native audio, 10 keyframes and omni reference. 3–30s, 720p / 1080p / 4K, aspect ratios 16:9, 9:16, 1:1, 21:9, 4:3, 3:4.
- **Kling 4.0 Flash** — Faster, lower-cost Kling 4 drafts — up to 20s at 720p. 3–20s, 720p, aspect ratios 16:9, 9:16, 1:1, 21:9, 4:3, 3:4.
- **Grok Imagine** — xAI’s video model with sound — 6 to 30 seconds from text or images. 6–30s, 480p / 720p / 1080p, aspect ratios 16:9, 9:16, 1:1, 2:3, 3:2.

## Inside the Whisk AI toolkit

- **Labelled remix slots** — Subject, Scene and Style each have their own slot, and some models take up to 16 reference images in total.
- **Prompt optional** — Fill a slot and press Generate. Words help steer the result, but they are never required.
- **Nano Banana and GPT Image** — Remix with Google’s Nano Banana family or OpenAI’s GPT Image family, picked per run.
- **Up to 4K** — Draft at 1K, then render the keeper at 2K or 4K on models that support it.
- **Any shape** — Square for stickers, 4:5 for feeds, 9:16 for stories, 16:9 for banners, or auto.
- **Reuse and run again** — Every result remembers its slots, prompt and model. Reuse them to make variations in one click.
- **Animate this** — Turn a finished remix into a short video with Seedance, Veo 3.1, Kling 4 or Grok Imagine.
- **Pay per image** — One credit balance, images from 6 credits, and failed renders are refunded automatically.
- **Private mode** — Paid plans can keep remixes out of the public gallery. Uploads are only used for your own runs.

## Whisk AI use cases across industries

- **Merch and print-on-demand** — Turn a mascot or pet into stickers, pins and plush mockups before you order a single sample.
- **E-commerce listings** — Place one product photo in new seasonal scenes and styles for listings, ads and email.
- **Social posts** — Remix a selfie into a poster, a clay figure or a watercolor for feeds and stories.
- **Characters and games** — Keep one character consistent while you try outfits, worlds and art styles.
- **Marketing and events** — Mock up campaign visuals, flyers and banners in your brand look in minutes.
- **Classrooms and storytelling** — Illustrate stories and lessons by combining a hero, a setting and a picture-book style.

## Whisk AI remixes made by creators

- **Seedance 2.0** (video, by @aimikoda) — A painterly animated romantic drama follows a young courier and a young mechanic racing through a decaying galactic port during their final minutes together. The Courier wears a weathered crimson travel coat and carries one small flight bag; the Mechanic wears a dark work jacket marked by luminous machine dust. Keep their faces, clothing, and bag consistent throughout. Use an Arcane-inspired visual style: sculpted 3D characters finished with expressive hand-painted textures, visible brushwork, graphic silhouettes, fractured colored light, atmospheric depth, painterly motion smears, selective f…
- **Seedance 2.0** (video, by @user_589415fe) — 4 cute clay 3D characters together, white background, fast cute story in 8 seconds: 0-2s group bouncy hug (boing pop), 2-3s look at blank sign sad tilt head (bloop sad), 3-6s fast montage all working together funny - sewing, hanging lights, kicking balloons, stacking books (whoosh boop patter pop fast), 6-8.5s big celebration confetti dance jump together happy ending, loop, soft claymation, pastel colors, no text, no speech, no dialogueSound: boing pop, sad bloop, ding idea, fast boop whoosh patter, celebration popper and cheerful blips, 8 seconds, energetic
- **Seedance 2.0** (video, by @user_589415fe) — YouTube Shorts 8 seconds, vertical 9:16, 4 cute clay 3D characters: pink beanie pink sweater, purple beanie colorful vest, pink pom beanie blue hair orange vest, lavender beanie backpack. Fast slapstick football comedy, white background, soft claymation.Timeline:0-2s: pink sweater kicks football hard (kick whoosh)2-4s: blue hair character runs funny to catch, steps, comically slips and slides long across floor (squeak + long whoooosh slide)4-6s: ball bounces off invisible wall, boomerangs back fast (boing boing whoosh)6-8s: ball bonks softly on his head (soft bonk boing), lands as hat, other 3…
- **Seedance 2.0** (video, by @TechieBySA) — “A cinematic 15-second video following a tiny needle-felted wool chibi figurine — dark tousled hair, natural skin tone with no blush, brown eyes, light blue “TechieSA” hoodie, blue pants, blue sneakers — through a cozy morning coffee routine. The entire world around him is miniature scale, photorealistic needle-felted wool texture throughout. [0:00–0:02] Open on a tight close-up of a tiny silver espresso machine sitting on a miniature wooden kitchen counter. Soft morning sunlight streams in from a small window to the left, casting a warm golden glow. Thin wisps of steam curl upward in the stil…
- **Seedance 2.0** (video, by @user_ead132f2) — Ultra-realistic cinematic commercial Premium food advertising quality. 4K HDR Photorealistic rendering. Extremely high detail. Physically accurate materials and lighting. Smooth cinematic motion. Stable object consistency. Fantasy grounded in realistic physics. Duration: 10 seconds. Aspect ratio: 16:9 Modern minimalist kitchen with a clean wooden table. Bright natural daylight enters through large windows. Warm neutral color palette. Soft shadows. Consistent lighting throughout the sequence. The table is clean except for cooking ingredients.Main character: young woman the character wearing a s…
- **Seedance 2.0** (video, by @abxxai) — Create a director-style PREVIS action storyboard focused on 8 continuous action frames using only minimal stick figures. No realistic anatomy, clothing, pants, shoes, or character details. Show only movement, camera choreography, momentum trails, and ink motion, with only a small amount of necessary text.” SUBJECTS A hiphop dancer wearing a loose white top and dark oversized pants with irregular ink erosion along the fabric edges; holding an oversized heavy ink brush in the right hand with dense wet ink; the brush is always part of the movement, generating visible ink trails and ink masses wit…
- **Seedance 2.0** (video, by @0xemotions_) — NAME: ISABELLA ROLE: HEAD CHEF CORE MOOD: Confident. Precise. In total command of her kitchen. VISUAL SIGNATURE: Every motion economical — nothing wasted, nothing rushed. Painterly digital illustration character sheet — soft angular faceted shading with gentle rounded plane transitions, warm directional lighting, fine confident linework, semi-realistic proportions. Plain neutral background. Woman, early 30s, olive skin, dark hair pulled into a sleek low bun, sharp focused eyes, fitted white chef's double-breasted jacket with sleeves rolled to the forearm, black apron, small gold hoop earrings.…
- **Seedance 2.0** (video, by @azed_ai) — 3D animated cinematic short, high-quality stylized realism. No BGM, no dialogue, no subtitles, no text, with ambient sounds. # Constraints Vary the framing and angles in every cut to avoid monotony. Focus on glass, liquid, steam, glowing ingredients, hand gestures, and cozy magical detail. Keep the magic subtle and elegant, not chaotic. # Character Young potion maker. Small round glasses, messy short hair, oversized sweater, ink-stained fingers. Curious, careful, slightly nervous, but deeply focused. # Setting A tiny potion shop at night. Wooden shelves filled with bottles, dried herbs, candle…
- **Seedance 2.0** (video, by @Weeleey6) — Woman = a young East Asian woman around 25, soft elegant features, shoulder-length dark hair, a gentle emotional face, wearing a cozy beige coat and a scarf. Tender and heartfelt. Appearance only. Man = a young East Asian man around 27, soft handsome features, neat dark hair, wearing a dark wool coat. Quietly emotional, restrained. Appearance only. Sreet = a quiet city street at night in light rain, rendered photorealistically — glistening wet pavement, warm glowing streetlights and shop signs, soft bokeh of city lights, a moody romantic atmosphere, umbrellas and reflections. Warm-and-cool cin…
- **Seedance 2.0** (video, by @Dheepanratnam) — Four-panel character model sheet in one row, evenly spaced, identical original character in every panel: panel 1 full-body front view standing upright, arms relaxed, both feet visible, not cropped; panel 2 full-body back view showing the plain yellow paper back with the glossy adhesive strip along the top edge, not cropped; panel 3 tight close-up of the face with a calm neutral expression; panel 4 tight close-up of the same character screaming in panic, mouth a wide scribbled open oval with jagged scribbled teeth, eyes huge spiral scribbles. Plain flat light-grey seamless background, soft even…
- **Seedance 2.0** (video, by @aiwithlumi) — Cinematic Wuxia sequence in an autumn maple forest: two martial artists, a female warrior in flowing pink-and-white silk Hanfu and a male warrior in blue robes, face off on wet mossy river rocks as golden sunbeams pierce mist and red maple leaves fall. She leaps into the air, draws her steel Jian, and glides toward him in dramatic slow motion before their blades clash with a burst of glowing sparks. She lands gracefully, splashing water around her, while a black sumi-e ink-wash effect spreads across the frame. End with a perfectly symmetrical wide shot of both warriors holding swords above the…
- **Seedance 2.0** (video, by @AllaAisling) — 15-second cinematic animated short. A narrow wooden suspension bridge crosses a spectacular mountain gorge. A young woman walks across the bridge. Suddenly, one suspension cable snaps. The bridge swings violently sideways. The woman drops to her knees and grips the wooden ropes. Several loose boards fall away beneath her. CUT TO: A gigantic dragon flies upward through the gorge. The dragon rises directly underneath the bridge. It catches the underside of the bridge with both front claws, gripping the heavy structural beams beneath the wooden walkway. The dragon remains completely below the bri…
- **Nano Banana Pro** (image, by @Preda2005) — Create a 3D isometric diorama illustration of an original character named [CHARACTER NAME], peacefully working or practicing a creative activity in a nature-inspired environment, sitting at a wooden desk near a large open window with sunlight flowing in and soft greenery visible outside. The character should be inspired by [ARCHETYPE / PROFESSION – e.g. writer, painter, meditator, calligraphy artist, tea master] and have a unique visual identity, including soft, natural clothing, organic textures, and a calm, introspective personality. The entire scene must have a handcrafted felt aesthetic, w…
- **Nano Banana Pro** (image, by @Naiknelofar788) — Surrounding the realistic main subject are multiple cute, 3D-style chibi miniatures of the same person, with identical facial features, hairstyle, body proportions, and outfit. The chibi figures are naturally distributed around the subject, interacting playfully with her or nearby elements in a charming, non-intrusive way. Overlay the image with vibrant, hand-drawn doodle effects: soft white outlines around the subject, playful sparkles, doodle hearts, tiny flowers, smiley icons, and floating white handwritten phrases like "shine", "bright day", and "happy". The style seamlessly blends hyper-r…
- **Nano Banana Pro** (image, by @Arminn_Ai) — An isometric 3D cube-shaped miniature room (shallow cutaway true cube; everything strictly contained within the cube). The room is [Room Description]. Character: a chibi/figurine-style — [Character Description]. The character is [Action], with a [Expression] expression. Figure material looks like matte PVC, with big head / small body proportions. Lighting: [Atmosphere Name]: [Light Sources]; realistic reflections and colored shadows. Camera: slightly elevated isometric three-quarter view, front cube edge centered; no elements protruding outside the cube. Photoreal materials with fine detail; n…
- **Nano Banana Pro** (image, by @Gdgtify) — 2x2 grid, 16:9, do this for 4 famous cities: M₁ PERSONIFIED ICON MASCOT (master) the place's most iconic figure/monument personified as a friendly mascot character (face, hair, pose), central and dominant. ¬M₁ = no mascot / generic person / monument not personified / mascot not of the place. M₂ COSTUME = CITY COLLAGE the mascot's garment/body is a collage of the city's skyline/landmarks/districts (buildings, bridge, subway, park, road); the costume reads as the place's map. ¬M₂ = plain costume / collage unrelated / single landmark. M₃ ANTHROPO‑ICON FRIENDS ≥4 of the city's symbols (food, trans…
- **Nano Banana Pro** (image, by @harboriis) — A high quality mixed media portrait of a trendy young man (using my uploaded person photo) standing on a train station platform at night. The subject is posing coolly, holding the strap of an olive backpack with one hand. He is wearing a stylish streetwear outfit with an oversized layered black hoodie, gray sweatpants, and chunky sneakers. The background features a realistic KRL Jabodetabek Commuter Line train side view with its signature red striping, with the train doors wide open, bathed in bright cinematic station lighting and city night ambiance. Surrounding the realistic main subject are…
- **GPT Image 2** (image, by @Naiknelofar788) — Create a stylish modern travel poster inspired by risography about [City Name]. Use simplified illustrated images of the city: the Gwanganje Bridge, ocean waves, seagulls, beach umbrellas, fish baskets at the market, neon street signs and small abstract decorative figures. Create a bold, multi-layered risographic poster with imperfect ink design, translucent colors printed on top, graininess in semitones, rough paper texture, flat graphic shapes, playful geometric shapes, and energetic editorial composition. Use fluorescent pink, bright blue, warm yellow, orange-red, leafy green, and rich coba…
- **GPT Image 2** (image, by @SimplyAnnisa) — Create a stylish modern travel poster inspired by risography about [City Name]. Use simplified illustrated images of the city: the Gwanganje Bridge, ocean waves, seagulls, beach umbrellas, fish baskets at the market, neon street signs and small abstract decorative figures. Create a bold, multi-layered risographic poster with imperfect ink design, translucent colors printed on top, graininess in semitones, rough paper texture, flat graphic shapes, playful geometric shapes, and energetic editorial composition. Use fluorescent pink, bright blue, warm yellow, orange-red, leafy green, and rich coba…
- **GPT Image 2** (image, by @Taaruk_) — Create a vertical cozy home scrapbook poster inspired by the reference images. Combine a beautiful realistic interior photograph on the top half with a hand-drawn illustrated memory journal on the bottom half. Top section: A warm, bright and minimalist cozy home interior with natural cream walls, light wooden furniture, open wooden shelves filled with tiny ceramic houses, cute collectible figurines, miniature animals, books, framed artwork and handmade décor. Include a wooden desk or dining table, vintage radio, small lamp, flowers, baskets, ceramics and carefully arranged little objects. Soft…
- **GPT Image 2** (image, by @Naiknelofar788) — Create a sophisticated minimalist editorial art poster featuring [Subject] as the central subject, inspired by premium travel photography and refined hand-drawn illustration. Preserve the subject’s recognizable identity, proportions, silhouette, defining details, and visual character. Combine realistic elements with elegant artistic interpretation. Use a warm ivory paper background with a limited vintage color palette inspired by the subject’s location or personality. Add delicate ink outlines, architectural sketch lines, subtle hatching, halftone texture, faded print effects, and soft waterco…
- **GPT Image 2** (image, by @Goodmanprotocol) — Create a premium 4:5 vertical Instagram travel poster for [Country], designed as part of a cohesive collectible “Souvenir Box” series. Show an open vintage cardboard travel box containing exactly 10 culturally authentic souvenirs from [Country]: 1 hero object, 2–3 supporting objects, and additional smaller keepsakes. Choose objects with varied materials, sizes, shapes, and cultural significance. Include exactly 4 paper elements: - A folded illustrated map showing 4 different destinations - A perforated vintage travel ticket - A die-cut [Country] destination sticker - One culturally appropriate…
- **GPT Image 2** (image, by @user_ed334ac7) — Create a stylish illustrated digital collage / character mood-board of a fashionable young African man in a playful sketchbook aesthetic. The composition should feature multiple poses and expressions of the same man arranged across a clean white background like a personalized personality poster or lifestyle board. Include one full-body central pose as the main focus, surrounded by smaller poses, selfies, close-up portraits, sitting poses, relaxed candid moments, and a cute chibi version.He should wear:tinted fashionable sunglassesfitted neutral-toned t-shirt or sleeveless topslim dark jeanstre…
- **GPT Image 2** (image, by @user_1233d897) — A cutting-edge commercial 3D isometric illustration of a modern creative workspace, designed for a premium SaaS website hero section. Behance and Dribbble trend-setting style. The composition features a stylized, soft-edged hovering desk in the center. On the desk rests a clean, futuristic glass tablet glowing with a soft holographic interface, surrounded by floating geometric elements like 3D spheres, sleek metallic cylinders, and matte clay-textured coffee cups. High-end C4D rendering, Octane Render, claymation aesthetic with glossy and matte contrasts. Dopamine color palette featuring vibra…
- **GPT Image 2** (image, by @user_b9ad198a) — Create a highly detailed, premium travel-art illustration featuring a hand holding a white HỒ CHÍ MINH Transit Pass in the foreground. The ticket must look like a real transit ticket with visible text elements including: city name “HỒ CHÍ MINH”, ticket type “HỒ CHÍ MINH Transit Pass”, fare amount, validity date, and a realistic black QR code on the right side. The ticket acts as a portal to HỒ CHÍ MINH, with a realistic miniature city scene emerging from the ticket cutout. A signature transportation element — the city’s most recognizable local vehicle, train, tram, bus, or monorail — breaks ou…
- **GPT Image 2** (image, by @user_3a66c469) — PROMPT:A premium editorial infographic poster in 16:9 horizontal format about Ancient Rome, designed like a luxury illustrated history atlas page, with a warm ivory parchment background, deep navy serif typography, and subtle gold accent details, featuring a dramatic central floating miniature cityscape of ancient Rome with the Colosseum, Roman forums, marble temples, triumphal arches, roads, statues, and layered hills in a cinematic diorama composition with soft clouds and golden sunlight, highly detailed and realistic but stylized; on the left side a refined vertical information column with…

## Whisk AI pricing

## Subscriptions (monthly or yearly, cancel anytime)

- **Starter: $29.99/month or $288.00/year** — 2,400 credits per month.
- **Pro: $69.99/month or $624.00/year** — 5,200 credits per month.
- **Ultimate: $149.99/month or $1308.00/year** — 10,900 credits per month.
- **Crew: $79.00/month or $708.00/year per seat (min 3 seats)** — 5,900 credits per month.
- **Business: $119.00/month or $948.00/year per seat (min 3 seats)** — 7,900 credits per month.

## Credit packs (one-time, credits never expire)

- **Starter: $9.90** — 600 credits, never expire.
- **Creator: $29.90** — 2,200 credits, never expire.
- **Studio: $49.90** — 4,200 credits, never expire.
- **Business: $99.90** — 10,000 credits, never expire.

## Credit usage

| Model | Resolution | Credits |
| --- | --- | --- |
| Veo 3.1 Fast | 720p | 81 per video |
| Veo 3.1 Fast | 1080p | 87 per video |
| Veo 3.1 Fast | 4K | 241 per video |
| Veo 3.1 Quality | 720p | 335 per video |
| Veo 3.1 Quality | 1080p | 341 per video |
| Veo 3.1 Quality | 4K | 495 per video |
| Veo 3.1 Lite | 720p | 41 per video |
| Veo 3.1 Lite | 1080p | 47 per video |
| Veo 3.1 Lite | 4K | 201 per video |
| Seedance 2.5 | 480p | 38 per second |
| Seedance 2.5 | 720p | 85 per second |
| Seedance 2.5 | 1080p | 212 per second |
| Seedance 2.5 | 4K | 336 per second |
| Seedance 2.5 Flash | 480p | 25 per second |
| Seedance 2.5 Flash | 720p | 55 per second |
| Seedance 2.0 | 480p | 26 per second |
| Seedance 2.0 | 720p | 55 per second |
| Seedance 2.0 | 1080p | 137 per second |
| Seedance 2.0 | 4K | 279 per second |
| Seedance 2.0 Fast | 480p | 16 per second |
| Seedance 2.0 Fast | 720p | 34 per second |
| Seedance 2.0 Mini | 480p | 6 per second |
| Seedance 2.0 Mini | 720p | 11 per second |
| Kling 4.0 | 720p | 39 per second |
| Kling 4.0 | 1080p | 57 per second |
| Kling 4.0 | 4K | 133 per second |
| Kling 4.0 Flash | 720p | 23 per second |
| Grok Imagine | 480p | 4 per second |
| Grok Imagine | 720p | 7 per second |
| Grok Imagine | 1080p | 11 per second |
| Nano Banana Pro | 1K | 25 per image |
| Nano Banana Pro | 2K | 25 per image |
| Nano Banana Pro | 4K | 33 per image |
| Nano Banana 2.1 | 1K | 6 per image |
| Nano Banana 2.1 | 2K | 9 per image |
| Nano Banana 2.1 | 4K | 13 per image |
| Nano Banana 2 | 1K | 11 per image |
| Nano Banana 2 | 2K | 17 per image |
| Nano Banana 2 | 4K | 25 per image |
| Nano Banana 2 Lite | 1K | 6 per image |
| Nano Banana | 1K | 6 per image |
| GPT Image 2.5 Flare | 1K | 9 per image |
| GPT Image 2.5 Flare | 2K | 14 per image |
| GPT Image 2.5 Flare | 4K | 22 per image |
| GPT Image 2.5 Sunburst | 1K | 9 per image |
| GPT Image 2.5 Sunburst | 2K | 14 per image |
| GPT Image 2.5 Sunburst | 4K | 22 per image |
| GPT Image 2 | 1K | 9 per image |
| GPT Image 2 | 2K | 14 per image |
| GPT Image 2 | 4K | 22 per image |
| GPT Image 2.6 Economy | 1K | 7 per image |
| GPT Image 1.5 | 1K | 6 per image |
| GPT Image 1.5 | 2K | 30 per image |
| GPT Image 1 (4o) | 1K | 9 per image |

Credits are only charged for successful renders. Refunds: within 7 days of purchase if no more than 10% of the pack's credits were used.

## Whisk AI FAQ

### What is Whisk AI?

Whisk AI (WhiskAI on whiskai.net) is an online image remixer. You give it up to three pictures, a subject, a scene and a style, plus an optional prompt, and it generates one new image that combines them using Nano Banana or GPT Image. You can then animate the result into a short video.

### Is this Google’s Whisk?

No. WhiskAI is an independent service that offers a Whisk-style subject, scene and style workflow. It is not affiliated with, endorsed or sponsored by Google, and Whisk and Google are trademarks of Google LLC.

### What happened to Google Whisk?

Google launched Whisk as a Google Labs experiment in December 2024. Labs tools change often, so check labs.google for its current status. If you want the remix workflow with your choice of Nano Banana or GPT Image and one credit balance, Whisk AI is an independent alternative.

### Do I need to write a prompt?

No. Fill at least one slot and press Generate; Whisk AI tells the model what each image is for. A short prompt such as "as an enamel pin" helps steer the look. Without any image, the prompt alone works like a normal text-to-image generator.

### How many images can I combine?

The three labelled slots cover subject, scene and style. Models such as Nano Banana Pro accept up to 8 reference images in total, so you can add more references under the slots when you need them.

### Which AI models does Whisk AI use?

Remixes run on Google’s Nano Banana family (Nano Banana Pro is the default) or OpenAI’s GPT Image family. Videos made with Animate this run on Seedance, Veo 3.1, Kling 4 or Grok Imagine. We name the real model on every result.

### Is Whisk AI free to use?

New accounts get free credits, enough for a first remix. After that you pay per image with credits from a pack or a plan; the Generate button always shows the exact cost before you start, and failed renders are refunded.

### Can I use my Whisk AI remixes commercially?

Yes with any credit pack and with Pro and higher plans, under our Terms of Service. Make sure you have the rights to the photos you upload, especially people, logos and characters you do not own.

### Can I turn a remix into a video?

Yes. Press Animate this on any finished image. The video studio opens with your remix as the first frame; describe the motion and choose Seedance, Veo 3.1, Kling 4 or Grok Imagine.

### Are my uploads private?

Uploads are stored so the model can read them and are used only for your own generations. Results are public in the gallery by default; paid plans include private mode to keep them to yourself.


---

Source: https://whiskai.net/ · Site index for AI agents: https://whiskai.net/llms.txt · Full content: https://whiskai.net/llms-full.txt
