Image
DeepSeek Janus-Pro
Create an image from a text brief with DeepSeek Janus-Pro.
- Text to image
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for DeepSeek Janus-Pro. Review your own result before publishing.
A starting point.
Create an image from a text brief with DeepSeek Janus-Pro. Specify composition before exploring variations.
Before you publish.
Check object relationships and small details against the brief.
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
Send prompt and choose output_format for delivery.
temperature changes randomness; cfg_weight controls prompt guidance. Start with one image and quote before increasing num_images.
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 janus. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | — |
cfg_weight | Number | Optional | ≥ 1 · ≤ 20 |
enable_safety_checker | On/off | Optional | — |
num_images | Whole number | Optional | ≥ 1 · ≤ 16 |
output_format | Text | Optional | jpeg, png |
seed | Whole number | Optional | — |
temperature | Number | Optional | ≥ 0.1 · ≤ 2 |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use DeepSeek Janus-Pro through the API.
Start with this model ID for the endpoint featured on this page:
janus
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.