Z Image Turbo API
IntĂ©grez des capacitĂ©s performantes de gĂ©nĂ©ration dâimages par IA. Cette documentation fournit une rĂ©fĂ©rence API complĂšte, des guides d'intĂ©gration et des exemples de code pour aider les dĂ©veloppeurs Ă crĂ©er rapidement des applications dâimages IA.
Démarrage rapide
Réalisez votre premier appel API en deux étapes : soumettre une tùche, puis interroger son statut.
Soumettre une tĂąche
Envoyez une requĂȘte POST au point de gĂ©nĂ©ration pour obtenir un ID de tĂąche.
Interroger le statut
Utilisez lâID de tĂąche pour vĂ©rifier la progression jusqu'Ă obtenir lâURL de lâimage.
Authentification
Authorization: Bearer {YOUR_API_KEY}Remarque : Gardez votre clé API sécurisée et ne l'exposez pas dans du code cÎté client.
https://zimageturbo.ai/api/generate
Create a new image generation task. This endpoint is asynchronous and returns a task_id plus initial status; call /api/status to retrieve the final images.
ParamĂštres du corps
| Nom du paramĂštre | Type | Requis | Description |
|---|---|---|---|
| prompt | string | Oui | Text prompt for generation (max 1000 characters). |
| aspect_ratio | string | Oui | Aspect ratio for the generated image. Allowed values: 1:1, 4:3, 3:4, 16:9, 9:16. |
{
"code": 200,
"message": "success",
"data": {
"task_id": "task_1234567890",
"status": "IN_PROGRESS"
}
}https://zimageturbo.ai/api/status
Interroger l'Ă©tat et le rĂ©sultat dâune tĂąche.
ParamĂštres de requĂȘte
| Nom du paramĂštre | Requis | Description |
|---|---|---|
| task_id | Oui | LâID renvoyĂ© lors de la soumission. |
{
"code": 200,
"message": "success",
"data": {
"status": "SUCCESS",
"task_id": "xxxxxxxx",
"request": {
"prompt": "xxx",
"size": "1024*1024",
"seed": "-1"
},
"response": [
"https://xxx.com/sample.jpeg"
],
"consumed_credits": 15,
"created_at": "2025-12-05 13:05:09",
"error_message": null
}
}
Facturation
Coût par génération
Les tùches échouées ne sont pas facturées.
Gestion des erreurs
- 401 Non autoriséClé API invalide
- 402 Paiement requisSolde insuffisant
- 429 Trop de requĂȘtesLimite de requĂȘtes atteinte
Ă propos de Z Image Turbo
Z Image Turbo est un moteur de gĂ©nĂ©ration optimisĂ© sur les derniers modĂšles de diffusion, augmentant la vitesse dâinfĂ©rence Ă 300% des modĂšles traditionnels tout en maintenant une qualitĂ© Ă©levĂ©e.
Z-Image-Turbo â 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 backendsânot just offline batch jobs.
Why it looks so good?
- âą Photorealistic output at speed â Generates high-fidelity, realistic images that work for product photos, hero banners, and UI visuals without multi-second waits.
- âą Bilingual prompts and text â Understands prompts in English and Chinese, and can render multilingual text directly in the imageâhelpful for cross-market campaigns, posters, and screenshots.
- âą Low-latency, low-step design â Only 8 function evaluations per image deliver extremely low latency, ideal for chatbots, configuration tools, design assistants, and any âclick â imageâ experience.
- âą Friendly VRAM footprint â Runs well in 16 GB VRAM environments, reducing hardware costs and making local or edge deployments more realistic.
- âą Scales for bulk generation â Its efficiency makes large jobsâcatalogues, continuous feed images, or auto-generated thumbnailsâpractical without blowing up compute budgets.
- âą Reproducible generations â A controllable seed parameter lets you recreate a previous image or generate small, controlled variations for brand safety and experimentation.
How to use
- prompt â natural-language description of the scene, style, and any on-image text (English or Chinese).
- size (width / height) â choose the output resolution; supports square and rectangular images up to high resolutions (for example, 1536 Ă 1536).
- seed â set to -1 for random results, or use a fixed integer to make outputs reproducible.