Alibaba's fast bilingual image model
Z Image Turbo AI Image Generator
Z Image Turbo writes English and Chinese text straight into your images, from neon shop signs to product labels and poster headlines, for 0.25 credits an image.
Make street scenes with bilingual signs, product shots with printed labels, typographic posters, editorial portraits, food, interiors and concept art with Alibaba's 6B parameter Z Image Turbo. Every image on this page is one we made on Pixel Dojo, shown with the exact prompt behind it, so you can start from any of them.
0.25 credits ($0.02) per image. Included in every plan, from $10/month.
Already a member? Sign in
By Brian Lovett · Updated

What you can make with Z Image Turbo
Seven images we made with Z Image Turbo at the default 8 steps, 0.25 credits each: two bilingual labels and signs, a typographic poster, a portrait, an interior, a food photo and a piece of concept art. Each prompt reads like a shot list, so reuse it as is or swap in your own subject. Tap Use this prompt to start from any of them.

Night street photo at 9:16 with a bilingual neon sign. "LUCKY NOODLE" and 好运面馆 both print cleanly above the cook, framed by steam, rain slick pavement and passing umbrellas. Start from this prompt for storefronts and signage.
Candid street photograph at night, 35mm lens at chest height. A noodle cook in a white cap and a splattered canvas apron lifts a tangle of noodles out of a steaming wok at a tiny street stall, above him a glowing red and green neon sign reads "LUCKY NOODLE" over the Chinese characters "好运面馆". Rain slick pavement in the foreground mirrors the neon, clouds of steam rise into the light, two passersby with umbrellas blur past. Mixed tungsten and neon light, slight motion blur on the noodles, high ISO grain, documentary street photography.

Product shot at 4:3 with a bilingual label. "OOLONG" and 乌龙茶 print crisp on the tin, and a warm backlight turns the curl of steam and the wet stone gold. Swap in your own product and label text.
Low angle studio product photograph, 100mm macro lens. A matte charcoal ceramic tea tin with a cream paper label printed in bold black serif letters "OOLONG" above the red Chinese characters "乌龙茶" stands on a wet slab of dark basalt, beside it a small pale celadon cup of amber tea sends a curl of steam up into the light, a few rolled dry tea leaves scattered on the wet stone. One hard warm backlight from behind turns the steam and the water beads on the stone glowing gold, a soft cool fill on the label, deep charcoal background, crisp reflections in the wet stone, premium tea advertising photography.

Editorial portrait at 3:4. Freckles, fine lines, windblown silver hair and a warm laugh in soft overcast light, framed by a grey sea. Start from this prompt for character and campaign portraits.
Tight editorial portrait at eye level, 85mm lens. A woman in her sixties with a cropped silver pixie cut, round tortoiseshell glasses and a mustard yellow ribbed wool turtleneck laughs as she turns toward the camera, one hand pushing wind blown hair off her forehead, standing at the rail of a grey ferry with a pale sea horizon behind her. Overcast soft daylight, a thin cool rim light along her cheek, real skin texture with freckles and fine lines, shallow depth of field, muted teal and ochre color grade, fine 35mm film grain.

Architecture at 16:9. Straight verticals, a sculptural spiral stair and shafts of sun falling from a skylight grid, with one reader in a red coat for scale. Start from this prompt for interiors and architecture.
Wide interior architecture photograph, 24mm tilt shift lens with perfectly straight verticals. A brutalist concrete public library with a five story atrium, tiers of warm oak bookshelves on every level, a sculptural concrete spiral staircase in the center, shafts of late afternoon sun cutting through a grid of skylights and landing on long reading tables, one reader in a red coat sitting alone for scale. Warm sunlight against cool grey board formed concrete, dust floating in the light beams, architecture magazine photography.

Typographic poster at 3:4. The headline, venue, date and door time all print exactly as written on a flat Swiss grid of orange and cobalt. Swap in your own event and date.
A bold Swiss style concert poster in portrait format printed on off white paper. A huge tilted orange circle overlaps a deep cobalt blue rectangle. Giant black condensed sans serif letters read "TIDE SIGNALS" across the top, and below them smaller black type reads "LIVE AT PIER NINE" and then "SATURDAY 14 NOVEMBER". A thin black rule runs along the bottom above the words "DOORS OPEN AT EIGHT". Flat colors, crisp grid layout, subtle paper texture, every word spelled exactly as written.

Food photo at 4:3. Crusty bread tearing into a runny yolk, with crumbled feta, cilantro and chili flakes in a cast iron skillet under soft morning window light. Start from this prompt for menus and food posts.
Close food photograph from a 45 degree angle, 50mm lens. A black cast iron skillet of shakshuka with three glossy runny eggs, crumbled white feta, torn cilantro and red chili flakes sits on a worn olive wood table, a hand tearing a crusty piece of sourdough beside it, a rumpled linen napkin and a small dish of flaky salt nearby. Soft morning window light from the left, a wisp of steam rising, deep tomato red and fresh green palette, crisp crust texture, food magazine photography.

Concept art at 16:9. A giant turtle carries a lantern lit village and a gnarled pine through a misty sea at sunrise, with birds overhead and two tiny boats for scale. Start from this prompt for game and film worlds.
Epic wide concept art from a low camera just above the water. A colossal ancient stone turtle with a moss covered shell carries a small village of lantern lit wooden houses and a crooked pine tree on its back as it wades through a shallow misty sea at dawn, a flock of white birds circles its head and two tiny fishing boats drift nearby for scale. Soft pink and gold sunrise backlight through the mist, volumetric light rays, painterly matte painting detail, cinematic color grade.
Z Image Turbo at a glance: sizes, settings and price
Everything you can set on Pixel Dojo, with the pixel sizes of the files we got back at each aspect ratio.
| Feature | Z Image Turbo on Pixel Dojo |
|---|---|
| Price | 0.25 credits per image, at every size and step count |
| Text in images | English and Chinese, written in double quotes |
| Square 1:1 | 1024 x 1024 |
| Wide 16:9 | 1344 x 768 |
| Tall 9:16 | 704 x 1280 |
| Standard 4:3 | 1376 x 1024 |
| Portrait 3:4 | 1024 x 1392 |
| Inference steps | 1 to 8, default 8 for the most detail |
| Seed | Set one to bring the same image back |
| Custom LoRAs | Up to 3 per job, at the same price |
| Speed in our runs | Median 9.6 s from submit to finished image |
| Model | 6B parameter open weights model from Alibaba's Tongyi team, Apache 2.0 license |
Z Image Turbo vs Flux 2 Klein 4B on signs and lettering
We sent the same prompts to Z Image Turbo at 8 steps and to Flux 2 Klein 4B at its 1 MP setting, at the same aspect ratio. Z Image Turbo printed both lines of the bilingual neon sign and the florist's chalkboard exactly as written. Klein 4B costs 0.1 credits to Z Image Turbo's 0.25 and gave the florist a warmer, fuller portrait. Our pick: Z Image Turbo for anything with a sign, a label or a headline, in English or Chinese, and Klein 4B for low cost images without lettering or when you work from reference images.
Same prompt: Candid street photograph at night, 35mm lens at chest height. A noodle cook in a white cap and a splattered canvas apron lifts a tangle of noodles out of a steaming wok at a tiny street stall, above him a glowing red and green neon sign reads "LUCKY NOODLE" over the Chinese characters "好运面馆". Rain slick pavement in the foreground mirrors the neon, clouds of steam rise into the light, two passersby with umbrellas blur past. Mixed tungsten and neon light, slight motion blur on the noodles, high ISO grain, documentary street photography.
Z Image TurboZ Image Turbo: both lines of the sign print exactly, LUCKY NOODLE in English and 好运面馆 in Chinese.
Candid street photograph at night, 35mm lens at chest height. A noodle cook in a white cap and a splattered canvas apron lifts a tangle of noodles out of a steaming wok at a tiny street stall, above him a glowing red and green neon sign reads "LUCKY NOODLE" over the Chinese characters "好运面馆". Rain slick pavement in the foreground mirrors the neon, clouds of steam rise into the light, two passersby with umbrellas blur past. Mixed tungsten and neon light, slight motion blur on the noodles, high ISO grain, documentary street photography.
Flux 2 Klein 4BFlux 2 Klein 4B: the English LUCKY NOODLE line glows over a busy night stall full of steam and rain.
Candid street photograph at night, 35mm lens at chest height. A noodle cook in a white cap and a splattered canvas apron lifts a tangle of noodles out of a steaming wok at a tiny street stall, above him a glowing red and green neon sign reads "LUCKY NOODLE" over the Chinese characters "好运面馆". Rain slick pavement in the foreground mirrors the neon, clouds of steam rise into the light, two passersby with umbrellas blur past. Mixed tungsten and neon light, slight motion blur on the noodles, high ISO grain, documentary street photography.
Same prompt: Medium close shot at eye level, 50mm lens. A florist with rolled denim sleeves and a green canvas apron ties brown twine around a bouquet of orange ranunculus on a zinc counter, both hands visible, while a hand painted chalkboard behind her reads "FRESH CUT TODAY" in white letters. Soft window light from the right, buckets of tulips and eucalyptus in the background, shallow depth of field, natural color, 35mm film grain.
Z Image TurboZ Image Turbo: FRESH CUT TODAY spelled exactly on the chalkboard, and orange ranunculus tied with twine, as the prompt asked.
Medium close shot at eye level, 50mm lens. A florist with rolled denim sleeves and a green canvas apron ties brown twine around a bouquet of orange ranunculus on a zinc counter, both hands visible, while a hand painted chalkboard behind her reads "FRESH CUT TODAY" in white letters. Soft window light from the right, buckets of tulips and eucalyptus in the background, shallow depth of field, natural color, 35mm film grain.
Flux 2 Klein 4BFlux 2 Klein 4B: a warm, full portrait of the florist at her counter, for 0.1 credits.
Medium close shot at eye level, 50mm lens. A florist with rolled denim sleeves and a green canvas apron ties brown twine around a bouquet of orange ranunculus on a zinc counter, both hands visible, while a hand painted chalkboard behind her reads "FRESH CUT TODAY" in white letters. Soft window light from the right, buckets of tulips and eucalyptus in the background, shallow depth of field, natural color, 35mm film grain.
| Z Image Turbo | Flux 2 Klein 4B | |
|---|---|---|
| Credits per image | 0.25 | 0.1 |
| Bilingual neon sign | LUCKY NOODLE and 好运面馆 both exact | LUCKY NOODLE exact |
| Florist scene | FRESH CUT TODAY spelled exactly on the chalkboard | Warmer, fuller portrait of the florist |
| Pixels at 9:16 | 704 x 1280 | 768 x 1360 |
| Reference images | Text to image | Up to 5 |
| Best for | Signs, labels, posters and Chinese text | Low cost images and work from reference images |
How to get great results from Z Image Turbo
One leather journal prompt on seed 1729 at 2, 4 and 8 inference steps, plus 8 steps again on the same seed. The gold ATLAS OF TIDES lettering prints exactly at every step count, detail builds as the steps go up, and the same seed brings the same picture back.

2 steps, seed 1729: the ATLAS OF TIDES lettering is already exact, with a smooth, soft finish on the leather and the map.
Studio photograph from above at a slight angle, 70mm lens. A hand bound leather journal with a brass corner clasp lies on a dark walnut desk, its cover embossed in gold with the words "ATLAS OF TIDES", a fountain pen, a folded paper nautical chart and a small brass compass arranged beside it. Warm lamp light from the upper left, soft shadows, rich leather grain and wood texture, crisp focus on the lettering.

4 steps, same seed: leather grain and map lines fill in.
Studio photograph from above at a slight angle, 70mm lens. A hand bound leather journal with a brass corner clasp lies on a dark walnut desk, its cover embossed in gold with the words "ATLAS OF TIDES", a fountain pen, a folded paper nautical chart and a small brass compass arranged beside it. Warm lamp light from the upper left, soft shadows, rich leather grain and wood texture, crisp focus on the lettering.

8 steps, the default: the richest leather creases and the sharpest map lines, at the same 0.25 credits.
Studio photograph from above at a slight angle, 70mm lens. A hand bound leather journal with a brass corner clasp lies on a dark walnut desk, its cover embossed in gold with the words "ATLAS OF TIDES", a fountain pen, a folded paper nautical chart and a small brass compass arranged beside it. Warm lamp light from the upper left, soft shadows, rich leather grain and wood texture, crisp focus on the lettering.

8 steps again on seed 1729: the same picture comes back, so you can return to an image you like.
Studio photograph from above at a slight angle, 70mm lens. A hand bound leather journal with a brass corner clasp lies on a dark walnut desk, its cover embossed in gold with the words "ATLAS OF TIDES", a fountain pen, a folded paper nautical chart and a small brass compass arranged beside it. Warm lamp light from the upper left, soft shadows, rich leather grain and wood texture, crisp focus on the lettering.
- Put every word that must print in double quotes, in English or Chinese. Our neon sign printed "LUCKY NOODLE" and 好运面馆, and our tea tin printed "OOLONG" and 乌龙茶.
- Give text a role and a style. Our poster prompt asks for giant black condensed letters for the headline and smaller type for the venue and date, and ends with "every word spelled exactly as written".
- Leave steps at 8. The price is 0.25 credits at every step count, and 8 steps gave our journal the richest leather and the sharpest map.
- Set a seed when you find an image you like. Our two 8 step runs on seed 1729 came back as the same picture.
- Write the prompt like a shot list: lens and angle first, then the subject, one action, the light and the texture. Every prompt on this page follows that order.
- Add your own style or character with custom LoRAs, up to 3 per job at the same price.
Z Image Turbo pricing: 0.25 credits per image
Z Image Turbo is included in every Pixel Dojo plan, from $10/month, and each image uses 0.25 credits from your plan. The price is the same at every aspect ratio and every step count, so one credit covers four images.
Custom LoRAs and a fixed seed add nothing to the price, so you can dial in a look and come back to it for the same 0.25 credits.
We made every Z Image Turbo image on this page through the Pixel Dojo API at exactly this price, so the same prompts cost the same in the web tool or in your own app.
Z Image Turbo questions
What is Z Image Turbo?
Z Image Turbo is a 6B parameter text to image model from Alibaba's Tongyi team, built for fast photoreal images and clean text. On Pixel Dojo you type a prompt, pick one of five aspect ratios and generate, and it is also available through the Pixel Dojo API.
Is Z Image Turbo good at text in images, including Chinese?
Yes, it is its standout strength. Our neon sign printed "LUCKY NOODLE" and 好运面馆 exactly, our tea tin label printed "OOLONG" and 乌龙茶, and our concert poster printed all four lines as written. Put each string in double quotes and say where it goes.
How much does Z Image Turbo cost?
Z Image Turbo is included in every Pixel Dojo plan, from $10/month. Each image is 0.25 credits, the same at every aspect ratio and step count, with or without custom LoRAs.
How fast is Z Image Turbo?
Fast. Our images came back in as little as 7.6 s from submit to finished file, with a median of 9.6 s at the default 8 steps.
What image sizes does Z Image Turbo make?
Five aspect ratios. The files we got back measured 1024 x 1024 at 1:1, 1344 x 768 at 16:9, 704 x 1280 at 9:16, 1376 x 1024 at 4:3 and 1024 x 1392 at 3:4.
What do the steps, seed and LoRA settings do?
Steps run from 1 to 8 and default to 8, which gave our images the richest texture at the same price. A seed brings the same image back when you run the prompt again. Custom LoRAs, up to 3 per job, add your own style or character.
Is Z Image Turbo open source, and can I use the images commercially?
Yes. Alibaba's Tongyi team released the Z Image Turbo weights on Hugging Face under the Apache 2.0 license, which allows commercial use, and our Terms of Service assign you our rights in the images you make on Pixel Dojo.
Make your first Z Image Turbo image
Write a prompt above or start from any example on this page. One subscription covers every model on Pixel Dojo.
Start with Z Image Turbo