Image
Z Image Base
Z Image Base generates still images from text with sampling controls.
- Text to image
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Z Image Base. Review your own result before publishing.
A starting point.
Explore a scene’s materials and lighting while adjusting prompt adherence.
Before you publish.
Compare texture, geometry and unwanted elements at full size; higher settings need visual review.
Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.
Settings and model questionsCheck the available settings and guidance when preparing your input.
Inputs and settings
Supply prompt and use negative_prompt for exclusions. Keep seed fixed while testing guidance_scale and num_inference_steps independently.
Start num_images at 1; Raywake permits up to 4. Choose output_format as jpeg, png or webp, and leave acceleration unchanged during comparisons.
Inputs, all modes and APIModel IDs, current input limits and the API generation workflow.
Supported inputs
These fields come from the current studio form for z-image/base. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | — |
acceleration | Text | Optional | — |
enable_safety_checker | On/off | Optional | — |
guidance_scale | Number | Optional | ≥ 1 · ≤ 20 |
negative_prompt | Text | Optional | — |
num_images | Whole number | Optional | ≥ 1 · ≤ 4 |
num_inference_steps | Whole number | Optional | ≥ 1 · ≤ 50 |
output_format | Text | Optional | jpeg, png, webp |
seed | Whole number | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use Z Image Base through the API.
Start with this model ID for the endpoint featured on this page:
z-image/base
Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.
Check the current model schema for supported inputs and options. Other tasks may use different model IDs.
From quote to result.
Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.
Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.