About FLUX Deblur
FLUX Deblur takes a blurry photograph and returns a sharper version of the same scene, reconstructing fine detail while keeping faces, colours, objects, lighting and composition as they were. It needs no prompt and no mask: the whole frame is sharpened.
It is built on a FLUX.2 Klein 9B image-to-image fine-tune trained on blurry-to-sharp pairs, so it is fast enough for interactive and high-volume use. Inputs are limited to 4 megapixels.
Ready to build with FLUX Deblur?
Try FLUX Deblur in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/images/edit \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "flux-deblur",
"input_image": "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/ox_zoom_out_1926_1076.png",
"safety_tolerance": 2
}'Request parameters
Every field FLUX Deblur accepts in the request body. See the API reference for response formats.
POST
https://hub.oxen.ai/api/ai/images/edit| Field | Type | Required | Default | Description |
|---|---|---|---|---|
input_image | stringuri | Yes | — | Blurry image to sharpen, up to 4 megapixels. |
seed | integernullable | No | — | |
safety_tolerance | integer | No | 2 | Safety filter strictness, 0 is strictest.012345 |