seedinteger
The same seed and the same input given to the same version of the model will output the same image every time.
try-on
sandbase-ai/cat-vtonCatVTON is a virtual try-on model. It dresses the person in a photo with a garment from a second image, with controls for the covered body area, guidance, steps, and aspect ratio.
Try the model
Playground
Input
The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.
Advanced settings
020
The CFG (Classifier Free Guidance) scale is a measure of how close you want
the model to stick to your prompt when looking for a related image to show you. Range: 0 to 20.
150
The number of inference steps to perform. Range: 1 to 50.
The same seed and the same input given to the same version of the model
will output the same image every time.
Type of the Cloth to be tried on.
Options:
upper: Upper body cloth
lower: Lower body cloth
overall: Full body cloth
inner: Inner cloth, like T-shirt inside a jacket
outer: Outer cloth, like a jacket over a T-shirt Allowed values: upper, lower, overall, inner, outer.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Url to the garment image.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Url for the human image.
ResultIdle
Your output will appear here
Complete the inputs, then click Run.
try-on
CatVTON virtual try-on: dress the person in human_image_url with the garment in garment_image_url.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
aspect_ratio | 21:9 / 16:9 / 3:2 / 4:3 / 5:4 / 1:1 / 4:5 / 3:4 / 2:3 / 9:16 | — | Output frame shape. |
guidance_scale | number 0–20 | 2.5 | How strictly to follow the garment. |
num_inference_steps | integer 1–50 | 30 | More steps add detail and time. |
seed | integer | random | Fix it to compare prompt changes. |
cloth_type | upper / lower / overall / inner / outer | — | Which body area the garment covers. |
garment_image_url | image URL | — | Photo of the garment. |
human_image_url | image URL | — | Photo of the person. |
Billing
$0.00125 per image.
| Request | Price |
|---|---|
| One image | $0.0013 |
Failed runs are not charged.
Prompting
- Use a front-facing person photo and a flat garment photo.
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "sandbase-ai/cat-vton",
"cloth_type": "upper",
"guidance_scale": 2.5,
"human_image_url": "https://static.sandbase.ai/examples/bfl/flux-2/virtual-tryon/input_images_0.png",
"garment_image_url": "https://static.sandbase.ai/examples/bfl/flux-2/virtual-tryon/input_images_1.png",
"num_inference_steps": 30
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"2. Authentication
Create a SandBase API key and set it in your server environment. All requests use Bearer authentication.
export SANDBASE_API_KEY="YOUR_API_KEY"Keep the key on your server. Do not expose it in browser code or commit it to a repository.
3. Queue
Submit a request
POST to /v1/run with this model ID and its inputs. The request example above includes submission and polling.
Fetch request status and result
Use the returned run ID to poll until the status is completed, failed or timeout. Read output only after completed.
curl "https://api.sandbase.ai/v1/run/$RUN_ID" \
-H "Authorization: Bearer $SANDBASE_API_KEY"4. Files
Hosted files
Pass a publicly accessible file URL in the model’s image, video or audio field. Supported formats and limits are shown beside each Playground input.
Uploading images
Use the upload or replace control on supported image fields in the Playground. Video URL fields accept a hosted driving video; they do not imply video-upload support.
5. Schema
Input
cloth_typestring
Type of the Cloth to be tried on. Options: upper: Upper body cloth lower: Lower body cloth overall: Full body cloth inner: Inner cloth, like T-shirt inside a jacket outer: Outer cloth, like a jacket over a T-shirt
Possible values: "upper", "lower", "overall", "inner", "outer"
aspect_ratiostring
The aspect ratio of the generated image.
Possible values: "21:9", "16:9", "3:2", "4:3", "5:4", "1:1", "4:5", "3:4", "2:3", "9:16"
guidance_scalenumber
The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.
Default: 2.5
Minimum: 0
Maximum: 20
human_image_urlstring
Url for the human image.
garment_image_urlstring
Url to the garment image.
num_inference_stepsinteger
The number of inference steps to perform.
Default: 30
Minimum: 1
Maximum: 50
{
"model": "sandbase-ai/cat-vton",
"cloth_type": "upper",
"guidance_scale": 2.5,
"human_image_url": "https://static.sandbase.ai/examples/bfl/flux-2/virtual-tryon/input_images_0.png",
"garment_image_url": "https://static.sandbase.ai/examples/bfl/flux-2/virtual-tryon/input_images_1.png",
"num_inference_steps": 30
}Output
A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
No example output has been published yet. Use Playground → Result → JSON after a completed run to inspect your response.