aura/aura-sr
AuraSR upscales images 4x with a GAN-based model that is fast and consistent.
Model Inputs
Image to upscale (.jpg/.png/.webp)
Drag & drop a file here, or click to select
Supported formats: JPG, PNG, WEBP (max 10MB)
Upscaling factor. More coming soon.
Whether to use overlapping tiles for upscaling. Setting this to true helps remove seams but doubles the inference time.
Checkpoint to use for upscaling. More coming soon.
Result
Pricing
aura/
aura-sr
Pricing for Synexa AI models works differently from other providers. Instead of being billed by time, you are billed by input and output, making pricing more predictable.
For example, generating 100 requests costs about $0.60.
Check out our docs for more information about how per-request pricing works on Synexa.
| Provider | Price ($) | Saving (%) |
|---|---|---|
| Synexa | $0.006 | - |
| fal | $0.006 | same price |
Readme
AuraSR is a GigaGAN-derived 4x upscaler. Unlike diffusion upscalers it does not re-imagine content, which makes it predictable and quick - a good default for bulk asset enlargement.
Checkpoint v2 gives better quality at the same compute cost as v1. Enable overlapping_tiles to remove tile seams, at roughly double the inference time.