About FLUX Virtual Try-On
FLUX Virtual Try-On dresses the person in one image in the clothing from another, keeping their face, pose and the rest of the scene intact. The garment can be a flat-lay packshot or worn by someone else, and a single reference can carry a whole outfit. It is built for fitting rooms, social filters and other interactive uses where latency matters.
It takes a person image and a garment image, and a short prompt that refers to them as image 1 and image 2. The output follows the person image's resolution: inputs up to 4 megapixels are used as they are, and larger ones are downscaled to about 1 megapixel. Keeping both images near 1 megapixel gives the best balance of quality and speed.
Ready to build with FLUX Virtual Try-On?
Try FLUX Virtual Try-On 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-virtual-try-on",
"prompt": "The person of image 1, keeping exactly their face and pose, wearing the garment of image 2.",
"input_image": "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/ox_zoom_out_1926_1076.png",
"input_image_2": "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 Virtual Try-On accepts in the request body. See the API reference for response formats.
https://hub.oxen.ai/api/ai/images/edit| Field | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | "The person of image 1, keeping exactly their face and pose, wearing the garment of image 2." | What the result should show. Refer to the person as image 1 and the garment as image 2. |
input_image | stringuri | Yes | — | Person to dress (image 1). The output keeps this image's resolution, up to 4 megapixels. |
input_image_2 | stringuri | Yes | — | Garment to put on the person (image 2), as a flat-lay packshot or worn by someone else. One image can carry a whole outfit. |
seed | integernullable | No | — | |
safety_tolerance | integer | No | 2 | Safety filter strictness, 0 is strictest.012345 |