Samsung’s sketch to image will go multimodal with the galaxy s25 series

Samsung Announced New Capability to its sketch to image feature, which will Arrive with the upcoming Galaxy S25 Series, on Tuesday. The south korean tech giant plans to significantly expand its ai offerings this year with the one UI 7 operating system, which the company calls itgrated ai platform. ” Earlier, The Tech Giant teased New Capability for the Virtual Assistant Bixby, and Now, It Confirmed That Sketch to Image will support multimodal capabilitys. This means users will be able to generate images by including a text prompt.

Samsung’s sketch to image to get new ai features

In a newsroom postThe tech giant highlighted the new capability of sketch to image that users will get to experience with the galaxy s25 series. Notable, the feature was introduced with the Galaxy Z fold 6 and Z flip 6 Last Year and was Later Expanded to Several Other Smartphones and Tablets.

Currently, sketch to image is an assistive tool that can refine anything a user sketches using ai. This means one can scribble a few lines to rooughly draw an image of a house, and the tool can identify what the user is trying to create and then enhance it to look like a sketch Made by an artist. The ai feature can also generate the image in multiple styles.

However, with One UI 7Samsung is integrating sketch to image into drawing assistant and adding new features. With new Multimodal Capability, users can now sketch an object and then add a text prompt to transform the image into somenting else. Highlighting one example, the company said users can draw an image of a cat and type “spacesuit” to generate images of a cat wearing a space.

Users can be as descriptive as they want to get a detailed output. Notable, this was not possible earlier as the tool could only improve what was drawn. Samsung highlighted that the new version of the ai tool will let users bring their imagination to reality, and even create things that might be different to draw.

The new version of sketch to image will support both text prompts and voice prompts for ease of use. It already supports bot the s pen and finger as touch inputs to not restrict users to the accessory.