VACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.

fal-ai/wan-vace-14b/depth

VACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.

Inference

Commercial use

Schema

Playground API

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

fal-ai/wan-vace-14b/depth

Schema

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

Input

Prompt*

A confident woman strides toward the camera down a sun-drenched, empty street. Her vibrant summer dress, a flowing emerald green with delicate white floral embroidery, billows slightly in the gentle breeze. She carries a stylish, woven straw bag, its natural tan contrasting beautifully with the dress. The dress's fabric shimmers subtly, catching the light. The white embroidery is intricate, each tiny flower meticulously detailed. Her expression is focused, yet relaxed, radiating self-assuredness. Her auburn hair, partially pulled back in a loose braid, catches the sunlight, creating warm highlights. The street itself is paved with warm, grey cobblestones, reflecting the bright sun. The mood is optimistic and serene, emphasizing the woman's independence and carefree spirit. High resolution 4k

Type # to reference inputs.

Video URL*

Hint: Drag and drop video files from your computer, video from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted file types: mp4, mov, webm, m4v, gif

Preprocess

Additional Settings

Customize your input with more control.

Result

Idle

This generation takes approximately 1m.

What would you like to do next?

Your request will cost $0.08 per video second for 720p, $0.06 per video second for 580p, $0.04 per video second for 480p. Video seconds are calculated at 16 frames per second.

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

Input

Prompt*

Type # to reference inputs.

Video URL*

Hint: Drag and drop video files from your computer, video from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted file types: mp4, mov, webm, m4v, gif

Preprocess

Additional Settings

Customize your input with more control.

Result

Idle

This generation takes approximately 1m.

What would you like to do next?

Wan VACE 14B (Video to Video) API on fal