# Z-Image Turbo

> Tongyi-MAI's 6-billion parameter distilled text-to-image model optimized for speed, achieving high-quality generation in 8 steps or fewer with support for bilingual text rendering

## Quick Reference

- Model ID: z-image-turbo
- Creator: Alibaba
- Status: active
- Family: z-image
- Base URL: https://api.lumenfall.ai/openai/v1

## Specifications

- Max Resolution: 2048x2048
- Input Modalities: text, image
- Output Modalities: image

## Model Identifiers

- Primary Slug: z-image-turbo

## Dates


## Tags

image-generation, text-to-image, fast, open-weights

## Available Providers

### Replicate

- Config Key: replicate/z-image-turbo
- Provider Model ID: prunaai/z-image-turbo
- Pricing:
  - notes: ["PrunaAI optimized version of Tongyi-MAI Z-Image-Turbo", "Sub-second generation with 8 steps"]
  - source: official
  - currency: USD
  - components: [{"type" => "output", "metric" => "megapixel", "unit_price" => 0.005}]
  - source_url: https://replicate.com/prunaai/z-image-turbo
  - effective_at: 2026-01-02

### fal.ai

- Config Key: fal/z-image-turbo
- Provider Model ID: fal-ai/z-image/turbo
- Pricing:
  - source: official
  - currency: USD
  - components: [{"type" => "output", "metric" => "megapixel", "unit_price" => 0.005}]
  - source_url: https://fal.ai/models/fal-ai/z-image/turbo
  - effective_at: 2025-12-29


## Performance Metrics

Provider performance over the last 30 days.

### replicate

- Median Generation Time (p50): 1363ms
- 95th Percentile Generation Time (p95): 6969ms
- Average Generation Time: 2188ms
- Success Rate: 69.3%
- Total Requests: 127
- Time to First Byte (p50): 1375ms
- Time to First Byte (p95): 7239ms

### fal

- Median Generation Time (p50): 1733ms
- 95th Percentile Generation Time (p95): 7522ms
- Average Generation Time: 2411ms
- Success Rate: 92.3%
- Total Requests: 78
- Time to First Byte (p50): 1745ms
- Time to First Byte (p95): 7401ms


## Arena Benchmarks

### Modern Clean Menu

- Elo: 1257
- Record: 8W / 17L / 4T (29 battles)
- Rank: #2 of 19

### Adorable Baby Animals in Sunny Meadow

- Elo: 1193
- Record: 10W / 4L / 0T (14 battles)
- Rank: #6 of 23

### Fantasy Warrior

- Elo: 1189
- Record: 10W / 4L / 2T (16 battles)
- Rank: #8 of 19

### Geometric Composition

- Elo: 1169
- Record: 15W / 12L / 5T (32 battles)
- Rank: #11 of 22

### Heroic Super Hero Portrait

- Elo: 1164
- Record: 5W / 1L / 2T (8 battles)
- Rank: #11 of 19

### Vintage Cafe Logo

- Elo: 1158
- Record: 10W / 6L / 2T (18 battles)
- Rank: #9 of 19

### Victorian Greenhouse Oasis

- Elo: 1153
- Record: 12W / 12L / 4T (28 battles)
- Rank: #13 of 17

### Candid Street Photography

- Elo: 1143
- Record: 9W / 10L / 4T (23 battles)
- Rank: #15 of 22

### Fantasy Warrior

- Elo: 1137
- Record: 6W / 0L / 1T (7 battles)
- Rank: #3 of 14

### Isometric Miniature Diorama Scenes

- Elo: 1111
- Record: 7W / 14L / 2T (23 battles)
- Rank: #19 of 19

### Night Sky Transformation

- Elo: 1000
- Record: 0W / 22L / 0T (22 battles)
- Rank: #15 of 15

### Bald man challenge

- Elo: 999
- Record: 0W / 23L / 0T (23 battles)
- Rank: #14 of 14


## Use Cases & Category Performance

### Product, Branding & Commercial (Text-to-Image)

- Rank: #5 of 19
- Elo: 1201
- Record: 10W / 6L / 2T (18 battles)
- Win Rate: 55.6%

### Portrait (Text-to-Image)

- Rank: #7 of 19
- Elo: 1210
- Record: 10W / 4L / 2T (16 battles)
- Win Rate: 62.5%

### Photorealism (Text-to-Image)

- Rank: #12 of 22
- Elo: 1184
- Record: 9W / 10L / 4T (23 battles)
- Win Rate: 39.1%

### Text Rendering (Text-to-Image)

- Rank: #13 of 21
- Elo: 1213
- Record: 18W / 23L / 6T (47 battles)
- Win Rate: 38.3%

### Portrait (Image Editing)

- Rank: #14 of 14
- Elo: 1033
- Record: 0W / 23L / 0T (23 battles)
- Win Rate: 0.0%

### Photorealism (Image Editing)

- Rank: #16 of 16
- Elo: 1026
- Record: 0W / 45L / 0T (45 battles)
- Win Rate: 0.0%


## Image Gallery

16 images available for this model.
- Curated examples: 4
  - "A cinematic, wide-angle shot of a high-end, boutique camera store at twilight. The centerpiece is a large, elegant st..."
  - "A hyper-realistic close-up of an elderly artisan’s weathered hands meticulously carving intricate floral patterns int..."
  - "A hyper-realistic, macro close-up of a weathered leather craftsman's workbench. In the center, a pair of vintage bras..."
  - "A cozy street-side chalkboard sign with elegant, hand-lettered chalk typography that reads "Fresh Coffee & Warm Cooki..."
- Competition results: 12
  - Modern Clean Menu: #2 of 19 (Elo 1257)
  - Adorable Baby Animals in Sunny Meadow: #6 of 23 (Elo 1193)
  - Fantasy Warrior: #8 of 19 (Elo 1189)
  - Geometric Composition: #11 of 22 (Elo 1169)
  - Heroic Super Hero Portrait: #11 of 19 (Elo 1164)
  - Vintage Cafe Logo: #9 of 19 (Elo 1158)
  - Victorian Greenhouse Oasis: #13 of 17 (Elo 1153)
  - Candid Street Photography: #15 of 22 (Elo 1143)
  - Fantasy Warrior: #3 of 14 (Elo 1137)
  - Isometric Miniature Diorama Scenes: #19 of 19 (Elo 1111)
  - Night Sky Transformation: #15 of 15 (Elo 1000)
  - Bald man challenge: #14 of 14 (Elo 999)

## Example Prompt

The following prompt was used to generate an example image in our playground:

A cozy street-side chalkboard sign with elegant, hand-lettered chalk typography that reads "Fresh Coffee & Warm Cookies." Sunlight filters through autumn leaves, while a capybara calmly nps on a wooden bench in the soft-focus background.

## Code Examples

### Text to Image (Generation)

#### cURL

curl -X POST \
  https://api.lumenfall.ai/openai/v1/images/generations \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-image-turbo",
    "prompt": "A serene mountain landscape at sunset",
    "size": "1024x1024"
  }'

# Response:
# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

#### JavaScript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.lumenfall.ai/openai/v1'
});

const response = await client.images.generate({
  model: 'z-image-turbo',
  prompt: 'A serene mountain landscape at sunset',
  size: '1024x1024'
});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
console.log(response.data[0].url);

#### Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.lumenfall.ai/openai/v1"
)

response = client.images.generate(
    model="z-image-turbo",
    prompt="A serene mountain landscape at sunset",
    size="1024x1024"
)

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
print(response.data[0].url)

### Image Editing

#### cURL

curl -X POST \
  https://api.lumenfall.ai/openai/v1/images/edits \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -F "model=z-image-turbo" \
  -F "image=@source.png" \
  -F "prompt=Add a starry night sky to this image" \
  -F "size=1024x1024"

# Response:
# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

#### JavaScript

import OpenAI from 'openai';
import fs from 'fs';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.lumenfall.ai/openai/v1'
});

const response = await client.images.edit({
  model: 'z-image-turbo',
  image: fs.createReadStream('source.png'),
  prompt: 'Add a starry night sky to this image',
  size: '1024x1024'
});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
console.log(response.data[0].url);

#### Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.lumenfall.ai/openai/v1"
)

response = client.images.edit(
    model="z-image-turbo",
    image=open("source.png", "rb"),
    prompt="Add a starry night sky to this image",
    size="1024x1024"
)

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
print(response.data[0].url)


## About

## Overview
Z-Image Turbo is a 6-billion parameter text-to-image model developed by Alibaba’s Tongyi-MAI team. It distinguishes itself by utilizing distillation techniques to enable high-quality image synthesis in eight steps or fewer, making it significantly faster than standard diffusion models. The model is specifically optimized for bilingual text rendering, supporting both Chinese and English characters within generated imagery.

## Strengths
*   **Inference Latency:** By reducing the required sampling steps to a range of 1 to 8, the model provides near-instantaneous image generation suitable for real-time applications.
*   **Bilingual Text Rendering:** The model excels at accurately rendering complex Chinese characters and English text, a task where many Western-centric models often fail or produce "gibberish."
*   **Visual Fidelity at Low Step Counts:** Despite the aggressive distillation for speed, the model maintains high structural integrity and aesthetic consistency that typically requires 25-50 steps in non-distilled models.
*   **Multimodal Input Support:** It can process both text prompts and image-based references (image-to-image) to guide the generation process, offering flexibility beyond simple text descriptors.

## Limitations
*   **Fine Detail Saturation:** While excellent for rapid generation, the model may lack the extreme micro-detail or complex texture depth found in larger, 12B+ parameter models that utilize longer sampling chains.
*   **Step Count Sensitivity:** Moving beyond the 8-step threshold does not necessarily improve quality and can sometimes lead to visual artifacts, as the model is strictly tuned for low-step schedules.
*   **Stylistic Range:** Compared to broader foundation models, the output may lean toward a specific "polished" aesthetic favored by its distillation process, which might require more aggressive prompting to deviate from.

## Technical Background
Z-Image Turbo is part of the Z-Image model family and utilizes a distilled architecture derived from a larger latent diffusion framework. To achieve its speed, the developers employed a consistency-based distillation approach that maps the probability flow of the original model into a single or few-step inference trajectory. The integration of a specialized text encoder allows the model to handle bilingual tokens more effectively than models trained solely on English datasets.

## Best For
This model is ideal for interactive applications such as live drawing assistants, rapid prototyping for UI/UX design, and social media content creation where speed is prioritized over granular control. It is also a leading choice for projects requiring accurate Chinese typography within images. Z-Image Turbo is available for integration and testing through Lumenfall’s unified API and interactive playground.

## Frequently Asked Questions

### How much does Z-Image Turbo cost?

Z-Image Turbo starts at $0.005 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

### How do I use Z-Image Turbo via API?

You can use Z-Image Turbo through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "z-image-turbo". Code examples are available in Python, JavaScript, and cURL.

### Which providers offer Z-Image Turbo?

Z-Image Turbo is available through Replicate and fal.ai on Lumenfall. Lumenfall automatically routes requests to the best available provider.

### What is the maximum resolution for Z-Image Turbo?

Z-Image Turbo supports images up to 2048x2048 resolution.

## Links

- Model Page: https://lumenfall.ai/models/alibaba/z-image-turbo
- About: https://lumenfall.ai/models/alibaba/z-image-turbo/about
- Providers, Pricing & Performance: https://lumenfall.ai/models/alibaba/z-image-turbo/providers
- API Reference: https://lumenfall.ai/models/alibaba/z-image-turbo/api
- Benchmarks: https://lumenfall.ai/models/alibaba/z-image-turbo/benchmarks
- Use Cases: https://lumenfall.ai/models/alibaba/z-image-turbo/use-cases
- Gallery: https://lumenfall.ai/models/alibaba/z-image-turbo/gallery
- Playground: https://lumenfall.ai/playground?model=z-image-turbo
- API Documentation: https://docs.lumenfall.ai