Google for Virtual Try-On

ABOUT THE WORKFLOW

Try On Clothing Digitally
Upload a photo of a person and a separate photo of a garment. The model maps the body shape and pose, drapes the clothing with realistic folds and shadows, and returns the combined result. Works with tops, bottoms, and dresses.

Partner node. This workflow calls an external API, so each run uses credits from your API wallet. No API key needed. Floyo handles the connection.

Model

• Google Virtual Try-On (VTO) by Google, part of the Vertex AI Imagen family. Strong at realistic garment draping, accurate body preservation, and handling diverse body types and poses.

HOW IT WORKS

Step 1. Upload a person photo
A photo of the person who will wear the garment. Clear, well-lit, and showing enough of the body for the clothing type. A half-body shot works for tops. A full-body shot works for dresses and bottoms.
Works great with: front-facing poses · studio shots · lifestyle photos

Step 2. Upload a product photo
A separate photo of the clothing item on its own. Flat-lay shots, ghost mannequin images, and clean product photos on plain backgrounds give the best results.
Works great with: tops · bottoms · dresses

Step 3. Hit run and download
The model fits the garment to the person and returns the result. Preview it in the workflow, then download.
Ready for: e-commerce listings · lookbooks · social media · client presentations

First time? Leave every setting as-is. The defaults (1 image) are the right starting point for almost everyone.

RECOMMENDED SETTINGS

Quick-start guide. Find the goal that matches yours and copy the settings.

• Standard try-on (most people) — 1 image. Upload both photos and run. The right starting point for almost everyone.

• Want options to choose from — Raise the number of images to 2, 3, or 4 to generate several variations and keep the strongest.

• The fit looks off — Use a clearer person photo with the body visible and arms at the sides. Cropped or heavily posed shots make draping harder for the model.

• The garment details are blurry — Use a higher-resolution product photo with a clean background. Busy backgrounds and wrinkled fabric confuse the fit.

• Trying a dress or full-length item — Use a full-body person photo. A headshot or waist-up crop will not give the model enough body to work with.

• Product photo has a busy background — Swap it for a flat-lay or ghost mannequin shot on a white or transparent background. The model reads the garment shape from the product image, and clutter bleeds into the output.

Prompt: No prompt needed. This workflow takes two images and handles everything from there.

LEARN

📹 Videos

• Intro to Floyo

• ComfyUI 101 Free Course ft. Sebastian Kamph

• Floyo 101 for Team Collaboration

✨ Quick links

• Help docs

• LoRA Training guide

• Discover more workflows

USE CASES

🛍️ E-commerce & Product Listings
Show how a garment looks on a real body without booking a photoshoot for every SKU.

👗 Fashion Brands & Designers
Preview new designs on different body types before sampling. Test colourways and silhouettes on realistic figures without physical prototypes.

📱 Social Media & Content Creators
Generate outfit-of-the-day visuals, style comparisons, or "which looks better?" content using product photos and a single selfie.

🏢 Retail Teams & Merchandising
Build internal lookbooks and seasonal previews by running garment photos against a consistent set of model shots, without coordinating a full studio shoot.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• Front-facing, well-lit person photos

• Flat-lay or ghost mannequin product shots on clean backgrounds

• Tops, bottoms, and dresses

• Diverse body types and natural poses

⚠️ May produce softer results

• Shoes, hats, bags, and accessories (not supported)

• Person photos where the body is mostly hidden or cropped

• Heavily layered outfits or multi-garment combinations

• Product photos with busy backgrounds or excessive wrinkles

FAQ

What is Google Virtual Try-On?
Google Virtual Try-On is a model from Google's Vertex AI Imagen family. It takes two images, a person and a garment, and generates a realistic composite showing the person wearing that item. It uses a diffusion model trained to understand body shape, pose, and fabric draping.

What clothing types does Google Virtual Try-On support?
The model supports tops, bottoms, and dresses. Shoes, lingerie, swimwear, hats, and accessories are not supported. For the best output, use a product photo that shows the full garment on a clean background.

How many images can I generate per run?
You can generate 1 to 4 images per run. Each additional image adds to the API cost. Start with 1 to test the fit, then raise the count when you want variations to choose from.

Does the output have a watermark?
Yes. Google applies an invisible SynthID watermark to all images generated by the Virtual Try-On model. It does not change how the image looks, but it remains embedded in the file as an AI-generation marker.

Can I use Google Virtual Try-On output for commercial projects?
Google Virtual Try-On is a proprietary API model, so commercial use is governed by Google's terms. Commercial use is allowed under current terms, but outputs carry the SynthID watermark, and you need the rights to any person or product photo you upload. Review Google's current Vertex AI terms for your use case.

What kind of person photo works best for virtual try-on?
A well-lit, front-facing photo where the relevant body area is visible and unobstructed. Arms at the sides, fitted clothing, and a clean background all help the model read body shape accurately. Avoid heavy cropping, extreme poses, and photos where most of the body is hidden.

How to run Google Virtual Try-On online?
You can run Google Virtual Try-On online through Floyo. No installation, no setup, no API key to wire up. Open the workflow in your browser, upload your two images, and hit run. Free to try.

WHY FLOYO?

Floyo is the only platform with team collaboration for ComfyUI in the browser. You run workflows with no install. You share run history, assets, and models across your team. You pay only when you generate. Floyo supports open-source and closed-source models.

A designer runs an edit and likes the result. A teammate opens that exact run from shared history and keeps going. No file handoffs. No version confusion.

For studios and enterprise teams, Floyo adds private workspaces, pooled resources, and a team usage dashboard. Other ComfyUI cloud tools run for one person at a time. Floyo runs for the whole team, with transparent per-generation costs.

Ready to try it?
Upload a person photo and a garment photo, then hit run. No prompt, no settings to change.

→ Launch Workflow, Free

Questions? Watch the free course or check the FAQ above.