Black Forest Labs/flux-virtual-try-on/Released Jul 2026

FLUX Virtual Try-On

Dress a person in a garment from a reference image

Commercial use
Image
FLUX Virtual Try-On

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.

See what this model can do

A handful of real prompts and their outputs.

A woman in a park shown in a white t-shirt, a mustard-yellow raincoat packshot, and the woman wearing the raincoat.
Outerwear
Park Raincoat
"Layers an open raincoat over the existing outfit, keeping her face, pose and the park untouched."
A man in a grey t-shirt in a studio, a navy double-breasted blazer packshot, and the man wearing the blazer.
Tailoring
Double-Breasted Blazer
"Keeps the peak lapels and gold button layout of the reference while fitting it to his shoulders."
An older woman in a beige knit top at home, a floral silk bow blouse packshot, and the woman wearing the blouse.
Womenswear
Floral Silk Blouse
"Transfers a dense peony print and neck bow while her glasses, smile and room stay the same."
A young man in a white t-shirt on a city street, a green and cream varsity jacket packshot, and the man wearing the jacket.
Streetwear
Varsity Jacket
"Preserves the striped ribbing, leather sleeves and star patch on a jacket worn open over his t-shirt."
A woman in black separates on a rooftop, a red satin gown on a ghost mannequin, and the woman wearing the gown.
Eveningwear
Red Satin Gown
"Replaces a full outfit with a floor-length gown, rendering satin sheen and a train that pools on the ground."
A bearded man in a white t-shirt in a library, an oatmeal cable-knit cardigan packshot, and the man wearing the cardigan.
Knitwear
Cable-Knit Cardigan
"Carries over the cable pattern, shawl collar and wooden toggles while his glasses and pose stay the same."
A woman in black on a train platform, a denim jumpsuit packshot, and the woman wearing the jumpsuit.
Denim
Denim Jumpsuit
"Swaps a two-piece outfit for a one-piece jumpsuit with belt, pockets and stitching intact."
An older man in a blue shirt in a cottage garden, a sand linen suit packshot, and the man wearing the suit.
Tailoring
Linen Suit
"Replaces shirt and trousers with a full two-piece suit and white shirt, keeping linen texture and his smile."
A woman in a tank top and shorts on a beach boardwalk, a lemon-print sundress packshot, and the woman wearing the dress.
Summerwear
Lemon Print Sundress
"Maps a busy all-over print onto the body with the fitted bodice and flared skirt of the reference."

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.

POSThttps://hub.oxen.ai/api/ai/images/edit
FieldTypeRequiredDefaultDescription
promptstringYes"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_imagestring
uri
Yes
—
Person to dress (image 1). The output keeps this image's resolution, up to 4 megapixels.
input_image_2string
uri
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.
seedinteger
nullable
No
—
safety_toleranceintegerNo2Safety filter strictness, 0 is strictest.
012345