Image
ESRGAN Image Upscaler
Enlarge a source image with a selected RealESRGAN variant.
- Image editing
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for ESRGAN Image Upscaler. Review your own result before publishing.
A starting point.
Enlarge a source image with a selected RealESRGAN variant. Choose the model for the source type, such as a photograph or anime illustration.
Before you publish.
Compare at equal display size, then inspect the enlarged output for halos, altered faces and invented texture.
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 image_url, select model and choose scale. The Raywake schema accepts scale from 1 to 8 and PNG or JPEG output_format.
Review face for portraits. tile divides processing into tiles; the provider suggests a nonzero tile size when memory errors occur.
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 esrgan. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
image_url | Text | Required | — |
face | On/off | Optional | — |
model | Text | Optional | RealESRGAN_x4plus, RealESRGAN_x2plus, RealESRGAN_x4plus_anime_6B, RealESRGAN_x4_v3, RealESRGAN_x4_wdn_v3, RealESRGAN_x4_anime_v3 |
output_format | Text | Optional | png, jpeg |
scale | Number | Optional | ≥ 1 · ≤ 8 |
tile | 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 ESRGAN Image Upscaler through the API.
Start with this model ID for the endpoint featured on this page:
esrgan
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.