About Z-Image-Turbo
Tongyi-MAI/Z-Image-Turbo is an image generation model that excels in fast text-to-image generation with photorealistic outputs and accurate bilingual (English & Chinese) text rendering, while running efficiently on 16 GB VRAM devices.
Some other noteworthy features of Tongyi-MAI/Z-Image-Turbo include strong instruction adherence for prompt-following and an 8-step inference design that enables sub-second latency on data-center GPUs.
| Metric | Value |
|---|---|
| Parameter Count | 6 billion |
| Mixture of Experts | No |
| Multilingual | Yes |
| Quantized* | No |
*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.
Ready to build with Z-Image-Turbo?
Try Z-Image-Turbo in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/images/generate \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "z-image-turbo",
"prompt": "A woman with red curly hair wearing a red flannel shirt, sitting in front of a campfire, night-time, photorealistic, indy folk vibes.",
"num_inference_steps": 8,
"output_format": "webp"
}'Request parameters
Every field Z-Image-Turbo accepts in the request body. See the API reference for response formats.
https://hub.oxen.ai/api/ai/images/generate| Field | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | — | Prompt for generated image |
num_inference_steps | integer | No | 8 | Number of denoising steps. Recommended range is 28-50, and lower number of steps produce lower quality outputs, faster. Range: 1 – 50 |
seed | integernullable | No | — | Random seed. Set for reproducible generation |
output_format | string | No | "webp" | Format of the output imageswebpjpgpng |