TL;DR

Image Translate fits large batches of sprites or UI bitmaps that already bake text into the art. When keeping copy inside the bitmap is acceptable, it is a fast i18n pass: pick a target language, run generation, and get a same-size image with the scene mostly preserved and the labels switched. It is image-generation based—not a separate text-layer export—so layout and style stay in the pixels.

Image Translate rewrites text that sits inside a bitmap via model generation, then outputs a matching-size asset. No hand-redraw of every label is required for a first pass.

Step 1: Start from a source UI image

Use a game interface or scene sprite that already shows the source language. The example below is a Simplified Chinese UI frame (location name, NPC prompts, signs, backpack / settings labels).

Simplified Chinese game UI scene used as the Image Translate source

Step 2: Open Image Translate and set the target language

With the image selected, open the toolbar control for Image Translate.

Toolbar with Image Translate highlighted on the selected game UI image

In the AI Image Translate dialog, choose the target language (for example English), confirm the layer, then run Translate.

AI Image Translate dialog with target language set to English

Step 3: Review the same-size translated image

The result keeps the same dimensions as the source. On-image copy switches to the target language (location title, NPC prompts, shop / exit signs, backpack / settings, and similar labels).

Same-size English UI result after Image Translate, with cleared background showing as transparency
Checkerboard shows the alpha: the original scene background was cleared during generation.

Current runs often clear the original environment background and leave transparency (or a hard matte) instead of the source sky / scenery. Treat that as a known limitation; later product passes may keep the background intact.