Wan | 2.5 | Preview | Text to Image - AI Model

This text-to-image model turns detailed prompts into high-quality, realistic visuals across multiple styles, from photorealism to illustration. It excels at prompt adherence, producing coherent scenes, accurate text, and consistent characters, with outputs up to 1080p. Use clear, specific descriptions of subject, style, mood, and context to guide results; iterate by rephrasing or adding details for tighter control. Include style keywords (e.g., anime, watercolor, cinematic lighting) and specify layout when rendering text in images. Expect fast generation with a quality/speed trade-off at higher resolutions. Ideal for marketing visuals, concept art, product mockups, storyboards, and branded social content.

Output Example

Used Prompt

A grand gothic library bathed in moonlight, towering bookshelves curving into a perfect archway. In the center, a massive oak table holds scattered scrolls, ink quills, and a shimmering crystal orb. Light streams diagonally through a tall stained-glass window, casting colorful patterns on the marble floor. The scholar, in a dark velvet cloak embroidered with silver patterns, is frozen mid-gesture as he turns a page, his face illuminated by the glow of the orb. Photorealistic composition, dramatic perspective, ultra-detailed textures, oil-painting aesthetic with chiaroscuro lighting.

Negative Prompt

low resolution, error, worst quality, low quality, defects