Building Tancky AI: Turning Multiple Photos into One Scene
Описание и применение
Разработчики создали веб‑интерфейс Tancky AI, позволяющий загружать до четырёх изображений, назначать им роли и описывать композицию, после чего AI генерирует объединённое изображение с прозрачной стоимостью.
Задача
Combining multiple reference images into a coherent scene while controlling which elements stay fixed and which change.
Результат
The workflow enables rapid creation of product scenes and other multi‑image compositions with clear cost visibility and iterative refinement.
Рабочий процесс
- Upload up to four images (JPG, PNG, WebP) with a 16 MB limit per image.
- Assign each image a role (subject, setting, etc.) via a composition prompt.
- Optionally select a preset (group portrait, portrait background, furniture staging).
- Generate the image and inspect the full‑size result.
- Iterate by adjusting the prompt or image roles and regenerating.
- Verify key details (label text, facial features, scale) before publishing.
- Use the credit counter to ensure cost visibility before generation.
Доказательства
Its image combiner lets you upload up to four reference images and describe the composition you want to create.
The combiner puts image uploads and the prompt together in the main workspace. It accepts JPG, PNG, and WebP files, with up to four images and a 16 MB limit per image.
It also offers presets for group portraits, portrait backgrounds, and furniture staging.
The workspace displays the credit total beside the Generate action. The server checks submitted options against the page's pricing configuration.
- Дата записи: 2026-10-20T10:56:24.051Z