z-image/turbo

text-to-image

TURBO

Z-Image-Turbo is a 6 billion parameter text-to-image model that generates photorealistic images in sub-second time. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

INPUT

Loading parameter configuration...

OUTPUT

Idle

Your generated images will appear here

Configure your settings and click Run to get started

Your request will cost $0.01 per run. For $10 you can run this model approximately 1000 times.

Here's what you can do next:

Image-to-Video Image-to-Image

Parameters

Code Example
import requests
import time

# Step 1: Start image generation
generate_url = "https://api.atlascloud.ai/api/v1/model/generateImage"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
    "model": "z-image/turbo",
    "prompt": "A beautiful landscape with mountains and lake",
    "width": 512,
    "height": 512,
    "steps": 20,
    "guidance_scale": 7.5,
}

generate_response = requests.post(generate_url, headers=headers, json=data)
generate_result = generate_response.json()
prediction_id = generate_result["data"]["id"]

# Step 2: Poll for result
poll_url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"

def check_status():
    while True:
        response = requests.get(poll_url, headers={"Authorization": "Bearer $ATLASCLOUD_API_KEY"})
        result = response.json()

        if result["data"]["status"] == "completed":
            print("Generated image:", result["data"]["outputs"][0])
            return result["data"]["outputs"][0]
        elif result["data"]["status"] == "failed":
            raise Exception(result["data"]["error"] or "Generation failed")
        else:
            # Still processing, wait 2 seconds
            time.sleep(2)

image_url = check_status()

Install

Install the required package for your language.

bash

pip install requests

Authentication

All API requests require authentication via an API key. You can get your API key from the Atlas Cloud dashboard.

bash

export ATLASCLOUD_API_KEY="your-api-key-here"

HTTP Headers

python

import os

API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {API_KEY}"
}

Keep your API key secure

Never expose your API key in client-side code or public repositories. Use environment variables or a backend proxy instead.

Submit a request

import requests

url = "https://api.atlascloud.ai/api/v1/model/generateImage"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
    "model": "your-model",
    "prompt": "A beautiful landscape"
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

Submit a Request

Submit an asynchronous generation request. The API returns a prediction ID that you can use to check the status and retrieve the result.

POST/api/v1/model/generateImage

Request Body

import requests

url = "https://api.atlascloud.ai/api/v1/model/generateImage"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}

data = {
    "model": "z-image/turbo",
    "input": {
        "prompt": "A beautiful landscape with mountains and lake"
    }
}

response = requests.post(url, headers=headers, json=data)
result = response.json()

print(f"Prediction ID: {result['id']}")
print(f"Status: {result['status']}")

Response

{
  "id": "pred_abc123",
  "status": "processing",
  "model": "model-name",
  "created_at": "2025-01-01T00:00:00Z"
}

Check Status

Poll the prediction endpoint to check the current status of your request.

GET/api/v1/model/prediction/{prediction_id}

Polling Example

import requests
import time

prediction_id = "pred_abc123"
url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }

while True:
    response = requests.get(url, headers=headers)
    result = response.json()
    status = result["data"]["status"]
    print(f"Status: {status}")

    if status in ["completed", "succeeded"]:
        output_url = result["data"]["outputs"][0]
        print(f"Output URL: {output_url}")
        break
    elif status == "failed":
        print(f"Error: {result['data'].get('error', 'Unknown')}")
        break

    time.sleep(3)

Status Values

processingThe request is still being processed.

completedGeneration is complete. Outputs are available.

succeededGeneration succeeded. Outputs are available.

failedGeneration failed. Check the error field.

Completed Response

{
  "data": {
    "id": "pred_abc123",
    "status": "completed",
    "outputs": [
      "https://storage.atlascloud.ai/outputs/result.png"
    ],
    "metrics": {
      "predict_time": 8.3
    },
    "created_at": "2025-01-01T00:00:00Z",
    "completed_at": "2025-01-01T00:00:10Z"
  }
}

Upload Files

Upload files to Atlas Cloud storage and get a URL you can use in your API requests. Use multipart/form-data to upload.

POST/api/v1/model/uploadMedia

Upload Example

import requests

url = "https://api.atlascloud.ai/api/v1/model/uploadMedia"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }

with open("image.png", "rb") as f:
    files = {"file": ("image.png", f, "image/png")}
    response = requests.post(url, headers=headers, files=files)

result = response.json()
download_url = result["data"]["download_url"]
print(f"File URL: {download_url}")

Response

{
  "data": {
    "download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
    "file_name": "image.png",
    "content_type": "image/png",
    "size": 1024000
  }
}

Input Schema

The following parameters are accepted in the request body.

Total: 0Required: 0Optional: 0

No parameters available.

Example Request Body

json

{
  "model": "z-image/turbo"
}

Output Schema

The API returns a prediction response with the generated output URLs.

idstringrequired

Unique identifier for the prediction.

statusstringrequired

Current status of the prediction.

processingcompletedsucceededfailed

modelstringrequired

The model used for generation.

outputsarray[string]

Array of output URLs. Available when status is "completed".

errorstring

Error message if status is "failed".

metricsobject

Performance metrics.

predict_timenumber

Time taken for image generation in seconds.

created_atstringrequired

ISO 8601 timestamp when the prediction was created.

Format: date-time

completed_atstring

ISO 8601 timestamp when the prediction was completed.

Format: date-time

Example Response

json

{
  "id": "pred_abc123",
  "status": "completed",
  "model": "model-name",
  "outputs": [
    "https://storage.atlascloud.ai/outputs/result.png"
  ],
  "metrics": {
    "predict_time": 8.3
  },
  "created_at": "2025-01-01T00:00:00Z",
  "completed_at": "2025-01-01T00:00:10Z"
}

Atlas Cloud Skills

Atlas Cloud Skills integrates 300+ AI models directly into your AI coding assistant. One command to install, then use natural language to generate images, videos, and chat with LLMs.

Supported Clients

Claude Code

OpenAI Codex

Gemini CLI

Cursor

Windsurf

VS Code

Trae

GitHub Copilot

Cline

Roo Code

Amp

Goose

Replit

40+ supported clients

Install

bash

npx skills add AtlasCloudAI/atlas-cloud-skills

Setup API Key

Get your API key from the Atlas Cloud dashboard and set it as an environment variable.

bash

export ATLASCLOUD_API_KEY="your-api-key-here"

Capabilities

Once installed, you can use natural language in your AI assistant to access all Atlas Cloud models.

Image GenerationGenerate images with models like Nano Banana 2, Z-Image, and more.

Video CreationCreate videos from text or images with Kling, Vidu, Veo, etc.

LLM ChatChat with Qwen, DeepSeek, and other large language models.

Media UploadUpload local files for image editing and image-to-video workflows.

Learn more

github.com/AtlasCloudAI/atlas-cloud-skills

MCP Server

Atlas Cloud MCP Server connects your IDE with 300+ AI models via the Model Context Protocol. Works with any MCP-compatible client.

Supported Clients

Cursor

VS Code

Windsurf

Claude Code

OpenAI Codex

Gemini CLI

Cline

Roo Code

100+ supported clients

Install

bash

npx -y atlascloud-mcp

Configuration

Add the following configuration to your IDE's MCP settings file.

json

{
  "mcpServers": {
    "atlascloud": {
      "command": "npx",
      "args": [
        "-y",
        "atlascloud-mcp"
      ],
      "env": {
        "ATLASCLOUD_API_KEY": "your-api-key-here"
      }
    }
  }
}

Available Tools

atlas_generate_imageGenerate images from text prompts.

atlas_generate_videoCreate videos from text or images.

atlas_chatChat with large language models.

atlas_list_modelsBrowse 300+ available AI models.

atlas_quick_generateOne-step content creation with auto model selection.

atlas_upload_mediaUpload local files for API workflows.

Learn more

github.com/AtlasCloudAI/mcp-server

API Schema

Schema not available

Please log in to view request history

You need to be logged in to access your model request history.

Z-Image Turbo - Lightning-Fast Text-to-Image Generation

NEW

6 Billion Parameter Model by Alibaba TONGYIMAI

Z-Image Turbo is the #1 ranked open-source text-to-image model, surpassing FLUX.2 [dev], HunyuanImage 3.0, and Qwen-Image on the Artificial Analysis Image Arena. Built by Alibaba's Tongyi-MAI team (a separate division from Qwen/Wan), this 6B parameter model achieves sub-second generation through advanced Decoupled-DMD distillation while maintaining photorealistic quality. With only 8 inference steps, it fits within 16GB VRAM and delivers professional results optimized for speed-critical production environments.

Ultra-Fast Generation

Only 8 inference steps (vs 20-50 for competitors)
Sub-second generation on H800 GPUs
1.31-1.41× faster than Qwen Image per step
Fits in 16GB VRAM (RTX 3060/4090)

Photorealistic Quality

#1 ranked open-source model on AI Arena
Bilingual text rendering (English & Chinese)
Robust instruction adherence
Beats FLUX.1 [dev] and Qwen in all categories

Alibaba's Strategic Model Portfolio

Alibaba offers three specialized AI image generation systems, each optimized for different use cases

Speed Champion

Z-Image Turbo

Tongyi-MAI Team

Best For: Speed-critical production workloads

⚡ Fastest: 8 steps, sub-second generation
🏆 #1 ranked open-source model
💰 Most cost-effective ($0.005/image)
🎯 Optimized for rapid iteration

Quality King

Qwen-Image

Qwen Team

Best For: Maximum quality final renders

🎨 Unmatched photorealism & skin textures
💡 Superior lighting interactions
⏱️ Slower (20s vs 5-10s for Z-Image)
🎯 Best for high-end production work

Versatility Pro

Wan 2.5/2.6

Wan Team

Best For: Multimedia versatility

🎬 Text-to-Video + Image-to-Video
📹 Multi-resolution support (480P-720P)
🔄 Audio-visual synchronization
🎯 Cross-modal content generation

Key Insight: Z-Image Turbo is 1.31-1.41× faster than Qwen-Image per step, making it ideal for applications requiring rapid generation. While Qwen-Image offers slightly better photorealism for final renders, Z-Image Turbo provides the best balance of speed and quality for production environments.

Technical Highlights

Performance

S3-DiT Architecture

Adopts Single-Stream Diffusion Transformer (S3-DiT) architecture that unifies processing of various conditional inputs. This 6B parameter design achieves professional results without the computational overhead of larger models while maintaining state-of-the-art quality.

Speed

Decoupled-DMD Distillation

Advanced distillation algorithm with CFG Augmentation and Distribution Matching mechanisms enables 8-step inference (vs 20-50 for competitors). Achieves sub-second generation on H800 GPUs and runs smoothly on consumer RTX 3060/4090 with 16GB VRAM.

Quality

Leading Open-Source Performance

Ranked #1 open-source model on Artificial Analysis Image Arena, beating FLUX.2 [dev], HunyuanImage 3.0, and Qwen-Image. Excels at bilingual text rendering (English & Chinese), photorealistic generation, and robust instruction following. Released under Apache 2.0 license for commercial use.

Perfect For

🎨

Digital Art Creation

📸

Product Photography

📊

Marketing Materials

🎬

Concept Art

📱

Social Media Content

🖼️

Stock Photography

🎮

Game Assets

✨

Creative Prototyping

Why Choose Z-Image Turbo

⚡

Instant Results

Sub-second generation with zero cold start latency. Get your images immediately without any waiting.

💰

Cost-Effective

Affordable pricing at $0.005 per image. Scale your creative projects without breaking the budget.

🔌

Ready-to-Use API

Simple REST API integration. Start generating images in minutes with our comprehensive documentation.

Technical Specifications

Model Architecture6 Billion Parameters

Inference Steps8 NFEs (Number of Function Evaluations)

Generation SpeedSub-second on H800, 5-10s on consumer GPUs

VRAM Requirement16GB (RTX 3060/4090 compatible)

ArchitectureSingle-Stream Diffusion Transformer (S3-DiT)

Distillation MethodDecoupled-DMD with CFG Augmentation

LicenseApache 2.0 (Commercial Use Allowed)

Ranking#1 Open-Source on Artificial Analysis Arena

Pricing$0.005 per Image

Start Creating with Z-Image Turbo

Experience lightning-fast, photorealistic image generation today. No setup required, just call our API and start creating.

No cold starts - instant generation

Affordable pricing - $0.005 per image

Professional quality results

Z-Image-Turbo — 6B-parameter, ultra-fast text-to-image

Z-Image-Turbo is a 6B-parameter text-to-image model from Tongyi-MAI, engineered for production workloads where latency and throughput really matter. It uses only 8 sampling steps to render a full image, achieving sub-second latency on data-center GPUs and running comfortably on many 16 GB VRAM consumer cards.

Ultra-fast generation with production-ready quality

Where many diffusion models need dozens of steps, Z-Image-Turbo is aggressively optimised around an 8-step sampler. That keeps inference extremely fast while still delivering photorealistic images and reliable on-image text, making it a strong fit for interactive products, dashboards, and large-scale backends—not just offline batch jobs.

Why it looks so good?

Photorealistic output at speed Generates high-fidelity, realistic images that work for product photos, hero banners, and UI visuals without multi-second waits.
Bilingual prompts and text Understands prompts in English and Chinese, and can render multilingual text directly in the image—helpful for cross-market campaigns, posters, and screenshots.
Low-latency, low-step design Only 8 function evaluations per image deliver extremely low latency, ideal for chatbots, configuration tools, design assistants, and any “click → image” experience.
Friendly VRAM footprint Runs well in 16 GB VRAM environments, reducing hardware costs and making local or edge deployments more realistic.
Scales for bulk generation Its efficiency makes large jobs—catalogues, continuous feed images, or auto-generated thumbnails—practical without blowing up compute budgets.
Reproducible generations A controllable seed parameter lets you recreate a previous image or generate small, controlled variations for brand safety and experimentation.

How to use

prompt – natural-language description of the scene, style, and any on-image text (English or Chinese).
size (width / height) – choose the output resolution; supports square and rectangular images up to high resolutions (for example, 1536 × 1536).
seed – set to -1 for random results, or use a fixed integer to make outputs reproducible.

Pricing

Simple per-image billing:

Without prompt rewriting (prompt_extend=false): $0.015 per generated image
With prompt rewriting (prompt_extend=true): $0.03 per generated image

Try more models and see their difference!

Nano Banana Pro – Text-to-Image – Google’s Nano Banana Pro (Gemini 3.0 Pro Image family) delivers high-quality multi-image generation with extremely low cost per image, ideal for large-scale applications.
Seedream V4 – Text-to-Image – ByteDance’s high-resolution text-to-image model with rich detail and diverse styles, well suited for creative illustration and commercial visuals.
FLUX.2 [dev] – Text-to-Image – A lightweight FLUX.2-based base model hosted by AtlasCloud, optimised for efficient inference and LoRA-friendly training.

Paper

Tongyi-MAI/Z-Image-Turbo

Explore Similar Models

NEW

text-to-image

TURBO

Baidu ERNIE Image Turbo Text-to-image

A fast, low-latency version of ERNIE Image by Baidu, optimized for rapid iteration and scalable image generation.Balances speed and quality, ideal for real-time and high-throughput scenarios.

FREE

Free