Image
Recraft V3
Create a designed image from a prompt with Recraft V3.
- Text to image
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Recraft V3. Review your own result before publishing.
A starting point.
Describe the main shape, its placement and the intended visual style.
Before you publish.
Review text, silhouettes and color use; inspect the returned file before treating it as a finished design.
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
Provide prompt of up to 1,000 characters. Optional style chooses the visual treatment; colors supplies preferred colors.
Keep the composition description stable while changing style or palette. Use enable_safety_checker as provided by the form; this operation starts from text.
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 recraft/v3/text-to-image. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | Min. characters: 1 · Max. characters: 1000 |
colors | List | Optional | — |
enable_safety_checker | On/off | Optional | — |
style | Text | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use Recraft V3 through the API.
Start with this model ID for the endpoint featured on this page:
recraft/v3/text-to-image
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.