Drag and drop media files from your computer, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted: .jpg, .jpeg, .png, .webp
Ready to Generate
Configure your inputs and click run to generate an image preview.
WAN Video 2.7 is a cutting-edge multi-reference video generation model that maintains high consistency when using multiple images and videos as inputs. It supports up to 5 reference videos and multiple image inputs, achieving extremely natural and smooth movement without losing the details of characters and objects. Additionally, it is equipped with functions such as precise control of the first and last frames, as well as interactive video editing functions via natural language instructions.
In addition to beautiful high-resolution video up to 1080p, it also supports native audio synchronization, enhancing immersion in both audio and visual aspects. It adapts to a wide range of visual styles, including live-action, anime, 3D, and cyberpunk. With high controllability and cinematic-quality video aesthetics, it is an ideal solution for professional fields such as advertising, entertainment, and film production.
| Resolution | Credits Consumed |
|---|---|
| 720p(credits/s) | 4 |
| 1080p(credits/s) | 8 |
| Parameter | Specification |
|---|---|
| Core Capability | Reference image to video |
| Resolution | 720p,1080p |
| Aspect Ratio | 16:9,9:16,1:1,4:3,3:4 |
| Duration | 2,3,4,5,6,7,8,9,10 |

BytePlus
An innovative multimodal generative model that creates cinematic videos up to 30 seconds long from reference images.

BytePlus
A lightweight video generation model that quickly generates high-quality videos from reference images.

WAN
Next-generation model that transforms still images and audio into movie-quality videos with overwhelming generation speed

Google's fast multimodal video generation and editing model, which highly integrates audio and video

WAN
A next-generation integrated AI video generation model that achieves cinematic-level image quality and high consistency

Google's top-tier video generation model, crafting cinematic-level visuals and sound.