The company ShengShu Technology announced the launch of a new generation of image generation in Vidu Q2. Users have gained access to enhanced features, including “text-to-image,” “reference-to-image,” and full image editing. All these capabilities are available for free until December 31, 2025, with support for generation in 1080p resolution without limitations.
The updated Vidu Q2 allows for the creation of images based on text prompts, maintaining high quality and detail. The “reference-to-image” feature ensures consistency, preserving character traits, logos, and composition even when using multiple references. Additionally, users can quickly edit generated or uploaded images — changing objects, backgrounds, lighting, clothing, or correcting minor details.
Vidu Q2 supports image creation in 1080p, 2K, and 4K formats, suitable for producing posters, storyboards, advertising materials, covers for broadcasts, and social media. Generating one image takes about 5 seconds, allowing teams to quickly test ideas and prepare a large amount of material for projects of various scales.
One of the key advantages is the ability to use a shared workflow for images and videos based on a single model. This enables the creation of characters, environments, or key frames and transferring them unchanged into videos or new images, maintaining consistency and style within a single project. This allows teams to easily transition from illustration development to video production without the need to switch between different tools.
