Служба поддержки Wan

Wan is a large multimodal visual generation model from Tongyi Lab, Alibaba. Wan lets you easily turn your ideas into high-quality images and videos, giving you the freedom to create and experiment.
What's possible with Wan?
- Reference to Video (Starring): Cast characters from reference videos into new scenes. Supports human or human-like figures, enabling multi-person and human-object interactions with appearance and voice consistency.
- Image to Video: More stable and natural motion dynamics. Improved adherence to prompts. Excellent consistency with the source image in both subject and style.
- Text to Video: Precise cinematic control. Faithful recreation of sophisticated motion. Optimized for superior prompt interpretation and execution.
- Image Edit：Remove, modify, or add elements within your videos. Editing video is now as effortless as retouching a photo.
- Text to Image: Exceptional photorealism. Expressive multi-style aesthetics. Reliable and coherent prompt-following.
- Image Editing: Create and edit images with studio-quality levels of precision and control. Supports multi-image referencing for commercial-grade consistency and faithful aesthetic transfer.
- Sequential Image：Generate up to 12 consecutive images with consistent style and subjects. Move beyond single-image aesthetics into continuous visual storytelling.
Unleash your creativity with Wan.Читать далее