Wan-2.6 Video

Provided by FalLearn More

Wan 2.6 is an advanced AI video generation model featuring smart shot scheduling for multi-shot storytelling, higher-quality voice generation with stable multi-speaker dialogue, and natural, realistic voices. It accurately generates multi-shot sequences to express a full story while keeping key details consistent between shots, and can auto-plan scenes from simple prompts. Wan 2.6 supports video generation up to 15 seconds, creating 1080p videos at 24fps with native audio-visual synchronization, ensuring dialogue, music, and sound effects align perfectly with character movements and lip-sync. It includes video reference generation that uses a reference video for look and voice, then follows your prompt to create new clips. Supports text-to-video, image-to-video, and video-to-video generation.

Preview

Inputs

Prompt
text

The text prompt for video generation. For multi-shot videos, use format: 'Overall description. First shot [0-3s] content. Second shot [3-5s] content.'

Image Prompt
image

The image used as the first frame of the video.

optional: true
Video References
video
Accepts multiple

Reference videos for subject consistency. Videos' FPS must be at least 16 FPS. Reference in prompt as @Video1, @Video2, @Video3. Works for people, animals, or objects.

optional: true
Audio
audio

The audio to use as the background music. If the audio duration exceeds the duration value (5, 10, or 15 seconds), the audio is truncated to the first N seconds, and the rest is discarded. If the audio is shorter than the video, the remaining part of the video will be silent.

optional: true
Negative Prompt
text

The negative prompt is used to guide the model to avoid generating videos that contain certain elements or concepts.

optional: true
Seed
seed

The same seed and prompt will output the same video every time.

default: 48397minimum: 0maximum: 65535
Duration
dropdown

The duration of the generated video in seconds.

default: 5Accepts: 5s, 10s, 15s
Resolution
dropdown

The resolution of the generated video.

default: 1080pAccepts: 720p, 1080p
Aspect Ratio
dropdown

The aspect ratio of the generated video. This value is ignored when using video references.

default: 16:9Accepts: 16:9, 9:16, 1:1, 4:3, 3:4
Expand Prompt
toggle

Whether to expand the prompt using the model's own capabilities

default: true
Multi-Shots
toggle

When enabled, the model will generate a multi-shot video. If disabled, the model will generate a single-shot video.

default: true
Block NSFW
toggle

Whether to block NSFW content

default: false

Outputs

Generated Video
video

The generated video from the model.