HiNow LogoHiNow

Lucy VTON 3.5

Model Information

Display Name: Lucy VTON 3.5

API Model ID: decart/lucy-vton-3.5

Category: Video To Video

Description: Lucy VTON 3.5 is Decart's virtual try-on model for video. Give it a clip of a person plus a garment reference image and/or a text description of the outfit, and it dresses the subject realistically while preserving body shape, pose and motion across every frame. **Key Features:** - Video virtual try-on: substitute or add clothing and accessories - Works from a garment reference image, a descriptive prompt, or both (best: both) - Preserves identity, body shape and motion - Same duration as the input video **Capabilities:** - Replace tops, jackets, dresses, full outfits - Add accessories (glasses, hats, jewelry) - Match a specific product photo **Best For:** - E-commerce "try it on" experiences on recorded video - Fashion campaigns and lookbooks - Outfit variations from a single shoot **Technical Specs:** - Input: MP4 (H.264 or VP8), 16:9 or 9:16, up to 200 MB - Reference image: JPEG, PNG or WebP - Output: 720p MP4, same duration as input - Prompt pattern: "Substitute the current top with <garment description>" **Parameters:** | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | video | URL / base64 | Yes | Input video of the person (in `parameters.video`) | | prompt | string | No* | Outfit description (*required unless a garment image is given) | | images[0] / reference_image | URL / base64 | No | Garment reference image | | seed | integer | No | 0..4294967295 | | enhance_prompt | boolean | No | Auto-enhance the prompt (default true) | **Pricing:** billed per second of input video ($0.06/s).

How to Use This Model

To use Lucy VTON 3.5 via the HInow.ai API, use the model ID: decart/lucy-vton-3.5

API Request Example


POST https://api.hinow.ai/v1/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

{
  "model": "decart/lucy-vton-3.5",
  "messages": [
    {"role": "user", "content": "Your input here"}
  ]
}

Pricing

  • total: $0.06

Available Parameters

  • video: Input video of the person (URL or base64 data URI). MP4 H.264/VP8, 16:9 or 9:16, max 200 MB. Billed per second of this video.
  • reference_image: Garment reference image (URL or base64, JPEG/PNG/WebP). images[0] is accepted as an alias. Best results with image + descriptive prompt.
  • resolution: Output resolution (only 720p). (Options: 720p)
  • seed: Random seed for reproducibility (0-4294967295).
  • enhance_prompt: Let Decart rewrite/enhance the prompt automatically. Set false when your prompt is already detailed.

Quick Reference

To use this model, set: "model": "decart/lucy-vton-3.5"

Featured: No

Documentation: https://hinow.ai/models/decart/lucy-vton-3.5

API Endpoint: https://api.hinow.ai/v1

Back to Models

Lucy VTON 3.5

decart/lucy-vton-3.5

$0.060
per second

About

Lucy VTON 3.5 is Decart's virtual try-on model for video. Give it a clip of a person plus a garment reference image and/or a text description of the outfit, and it dresses the subject realistically while preserving body shape, pose and motion across every frame.

Key Features:

  • Video virtual try-on: substitute or add clothing and accessories
  • Works from a garment reference image, a descriptive prompt, or both (best: both)
  • Preserves identity, body shape and motion
  • Same duration as the input video

Capabilities:

  • Replace tops, jackets, dresses, full outfits
  • Add accessories (glasses, hats, jewelry)
  • Match a specific product photo

Best For:

  • E-commerce "try it on" experiences on recorded video
  • Fashion campaigns and lookbooks
  • Outfit variations from a single shoot

Technical Specs:

  • Input: MP4 (H.264 or VP8), 16:9 or 9:16, up to 200 MB
  • Reference image: JPEG, PNG or WebP
  • Output: 720p MP4, same duration as input
  • Prompt pattern: "Substitute the current top with <garment description>"

Parameters:

ParameterTypeRequiredDescription
videoURL / base64YesInput video of the person (in parameters.video)
promptstringNo*Outfit description (*required unless a garment image is given)
images[0] / reference_imageURL / base64NoGarment reference image
seedintegerNo0..4294967295
enhance_promptbooleanNoAuto-enhance the prompt (default true)

Pricing: billed per second of input video ($0.06/s).

Capabilities

Video To Video

Parameters

video

Input video of the person (URL or base64 data URI). MP4 H.264/VP8, 16:9 or 9:16, max 200 MB. Billed per second of this video.

reference_image

Garment reference image (URL or base64, JPEG/PNG/WebP). images[0] is accepted as an alias. Best results with image + descriptive prompt.

resolution

Output resolution (only 720p).

720p
seed

Random seed for reproducibility (0-4294967295).

enhance_prompt

Let Decart rewrite/enhance the prompt automatically. Set false when your prompt is already detailed.

Code Examples

curl -X POST https://api.hinow.ai/v1/videos \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $HINOW_API_KEY" \
  -d '{
    "model": "decart/lucy-vton-3.5",
    "prompt": "Enhance and upscale this video",
    "video_url": "https://example.com/video.mp4",
    "parameters": {
      "video": "",
      "reference_image": "",
      "resolution": "720p",
      "seed": "",
      "enhance_prompt": ""
    }
  }'