You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.

This is a Google model for virtual try-on: you upload an image of a person and an item, and the output is a frame with the clothing worn by the model. It is suitable for online stores, marketplaces, photo stocks, and content teams that need product cards and lookbooks without photoshoots.

The output is a finished image, not text. Quality depends on the source frames: the clearer the shot of the person and the item, the more accurate the fit and fabric texture. Output limit is up to 32,000 tokens, request context is 65,536 tokens.

Step-by-step reasoning mode is not noted for this model in our data — it is focused on generating images from uploaded frames. If you need detailed explanations or analysis, you can switch to a text model in the same window in BotHub.

Function calling and structured JSON output are not noted in our data: the model solves a visual task and returns an image. For scenarios with tools and strict schemas, use BotHub text models — a unified OpenAI-compatible API allows you to change models without rewriting the integration.

Images are not just supported, they are mandatory: without an input frame, the try-on will not start. Audio and video input are not noted in our data. Upload a photo of a person and a shot of the item, supplementing them with a text description of the desired result if necessary.

Uploaded images play the main role here, and text only clarifies the task, so language nuances have little effect on the result. The BotHub interface, payment with ruble cards, and support are in Russian; access from Russia works without a VPN or foreign card.