Image
Kolors
Create images from a visual brief with Kolors.
- Text to image
- Image editing
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Kolors. Review your own result before publishing.
A starting point.
Describe the composition, lighting and subject for a new image. Choose image-to-image when you want to reinterpret an existing picture.
Before you publish.
Inspect anatomy, lettering and small repeated details. For image-to-image, compare how much the source changed.
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. Adjust guidance_scale within 1–10 or num_inference_steps within 1–150 one at a time; preserve seed when comparing.
Begin with num_images set to 1 and select JPEG or PNG. Image-to-image requires image_url and prompt, with strength controlling the degree of change.
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 kolors. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | — |
enable_safety_checker | On/off | Optional | — |
guidance_scale | Number | Optional | ≥ 1 · ≤ 10 |
negative_prompt | Text | Optional | — |
num_images | Whole number | Optional | ≥ 1 · ≤ 8 |
num_inference_steps | Whole number | Optional | ≥ 1 · ≤ 150 |
output_format | Text | Optional | jpeg, png |
scheduler | Text | Optional | — |
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.
Other modes and their inputs
Open the operation you need and check its inputs. Settings from one mode do not automatically apply to another.
Image editingkolors/image-to-image
Supported inputs
These fields come from the current studio form for kolors/image-to-image. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
image_url | Text | Required | — |
prompt | Text | Required | — |
enable_safety_checker | On/off | Optional | — |
guidance_scale | Number | Optional | ≥ 1 · ≤ 10 |
negative_prompt | Text | Optional | — |
num_images | Whole number | Optional | ≥ 1 · ≤ 8 |
num_inference_steps | Whole number | Optional | ≥ 1 · ≤ 150 |
output_format | Text | Optional | jpeg, png |
scheduler | Text | Optional | — |
seed | Whole number | Optional | — |
strength | Number | Optional | ≥ 0.01 · ≤ 1 |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use Kolors through the API.
Start with this model ID for the endpoint featured on this page:
kolors
Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.
Available modes
- text-to-image ·
kolors - image-to-image ·
kolors/image-to-image
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.