Image
Omnigen V2
Generate or edit images using a prompt and optional image references.
- Text to image
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Omnigen V2. Review your own result before publishing.
A starting point.
For multiple references, identify which image supplies each object or visual detail.
Before you publish.
Check that referenced objects land in the intended scene and retain their defining features.
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
prompt is required; input_image_urls is optional for editing or combining references. Text-only requests can start without source images.
text_guidance_scale and image_guidance_scale adjust text and reference influence separately. Keep cfg_range_start, cfg_range_end and scheduler unchanged while first refining the brief.
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 omnigen-v2. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | — |
cfg_range_end | Number | Optional | ≥ 0 · ≤ 1 |
cfg_range_start | Number | Optional | ≥ 0 · ≤ 1 |
enable_safety_checker | On/off | Optional | — |
image_guidance_scale | Number | Optional | ≥ 1 · ≤ 3 |
input_image_urls | List | Optional | — |
negative_prompt | Text | Optional | — |
num_images | Whole number | Optional | ≥ 1 · ≤ 4 |
num_inference_steps | Whole number | Optional | ≥ 20 · ≤ 50 |
output_format | Text | Optional | jpeg, png |
scheduler | Text | Optional | — |
seed | Whole number | Optional | — |
text_guidance_scale | Number | Optional | ≥ 1 · ≤ 8 |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use Omnigen V2 through the API.
Start with this model ID for the endpoint featured on this page:
omnigen-v2
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.