Virtual try-on

Leffa

Meta's model for virtual try-on and changing a person's pose in a photo. Carefully transfers fine fabric details and lettering. MIT license, but the training data is non-commercial.

Developer
Meta AI (with King's College London), USA
First release
Dec 2024
Latest release
Dec 2024
Sizes
based on Stable Diffusion
License
Commercial use with conditionsMIT for code and weights, but the weights were trained on the VITON-HD and DressCode datasets with non-commercial terms — for business use, check with a lawyer
Running
On your own serverNeeds a GPU
Industries
Retail and marketplaces, Media and production
Deploy on your server Hugging Face GitHub

What it does

  • Trying clothes on a model photo
  • Changing the model pose in an existing shot
  • Adding extra angles for a product card

Where it is used

Online apparel retailMarketplacesPhoto studios and content teams

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
no versions
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Leffa: примерка (DressCode)
  2. Leffa: примерка (VITON-HD) и смена позы

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can Leffa be used in a commercial project?

With conditions. License: MIT for code and weights, but the weights were trained on the VITON-HD and DressCode datasets with non-commercial terms — for business use, check with a lawyer. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Leffa need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Leffa support Russian?

Language does not matter for this model: it does not work with text.

Where can I download Leffa and what does it cost?

The Leffa weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Virtual try-onIDM-VTONKAIST and OMNIOUS.AI · South KoreaNon-commercial only

One of the best-known open virtual try-on models: moves a garment from a product photo onto a photo of a person, keeping prints and logos well. Non-commercial license.

DetailsVirtual try-onFASHN VTONFASHN AI · IsraelCommercial use allowed

A rare open try-on model with a commercial license: mask-free, accepts a photo of the item on a model or a flat lay. Weights are about 2 GB.

DetailsVirtual try-onCatVTON / CatV2TONSun Yat-sen University and Pixocial · ChinaNon-commercial only

A lightweight try-on model that runs on a regular GPU. There is a mask-free version and CatV2TON, which also tries clothes on in video.

Details

Source: github.com/franciszzj/Leffa. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.