Wan-2.2 text-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts.

fal-ai/wan/v2.2-a14b/text-to-video

Wan-2.2 text-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts.

Inference

Commercial use

Schema

LLMs

Playground API

SandboxOpen in Sandbox

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

fal-ai/wan/v2.2-a14b/text-to-video

Schema

LLMs

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

Input

Prompt*

Number of Frames

Frames per Second

Additional Settings

Customize your input with more control.

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.

Result

Idle

What would you like to do next?

{
  "video": {
    "url": "https://storage.googleapis.com/falserverless/model_tests/wan/v2.2-woman-output.mp4"
  },
  "prompt": "A close-up of a young woman smiling gently in the rain, raindrops glistening on her face and eyelashes. The video captures the delicate details of her expression and the water droplets, with soft light reflecting off her skin in the rainy atmosphere."
}

AI Video Generation Guide - Wan 2.2

Easy Creation with One Click - AI Videos

Major Upgrade Announcement

Wan 2.2 Gets a Major Upgrade: More Beautiful and Fluid Video Generation!

Wan 2.2's video generation has received a comprehensive upgrade. It now includes both Text-to-Video and Image-to-Video functions and supports cinema-grade aesthetic controls. Users will experience more stable and fluid motion generation, a superior ability to follow instructions with greater real-world realism, and significantly faster generation speeds.

🚀 Key Features

🎨 Cinema-Grade Aesthetic Control

Integration the principles of professional cinematography—including lighting, color, and cinematic language—directly into the generation model. This allows for precise aesthetic control through multi-faceted keywords, resulting in visuals that are both stylistically diverse and rich in nuanced detail.

🎭 Greatly Improved Complex Motion Generation

Dynamic generation capabilities have continuously evolved, now enabling precise control and stable generation of highly complex movements. This includes nuanced body motion, athletic actions, and detailed facial expressions. The resulting motion is exceptionally fluid, with details rendered in a natural and realistic manner.

🌍 Enhanced Real-World Replication

Featuring significantly more powerful semantic control and instruction-following capabilities. This update brings remarkable improvements in multi-subject generation, the depiction of interactions, and spatial accuracy within complex scenes. As a result, users can now reliably replicate real-world scenarios through text prompts.

📝 Prompt Recipe Guide

Prompts are crucial for describing content and motion in videos, influencing visuals and effects. More complete and precise prompts lead to higher quality generated videos. Four "Prompt Recipe" formulas are provided, tailored to different usage needs.

🟢 Basic Formula

For new users trying AI video for the first time or seeking creative inspiration: Simple, open-ended prompts can generate more imaginative videos.

Formula: Prompt = Subject + Scene + Motion

Components:

Subject: The main focus of the video, which can be a person, animal, plant, object, or an imagined entity that may not physically exist.
Scene: The environment where the subject is situated, including background and foreground. It can be a real physical space or an imagined fictional setting.
Motion: This includes both the subject's specific movements and the general motion within the scene. It can range from stillness, subtle movements, and partial motions to large-scale or overall dynamic action.

🔵 Advanced Formula

For users with some experience in AI video creation: Adding richer, more detailed descriptions to the basic formula enhances video quality, vividness, and storytelling.

Formula: Prompt = Subject (Subject Description) + Scene (Scene Description) + Motion (Motion Description) + Aesthetic Control + Stylization

Components:

Subject Description: Details about the subject's appearance, described using adjectives or short phrases.
- Examples: "A black-haired Miao girl wearing ethnic minority clothing" or "A flying fairy from another world, dressed in tattered yet elegant attire, with a pair of strange wings made of rubble fragments."
Scene Description: Details about the environment where the subject is located, described using adjectives or short phrases.
Motion Description: Describes the characteristics of movement, including amplitude, speed, and effects of the motion.
- Examples: "Violently swaying," "Slowly moving," or "Shattering glass."
Aesthetic Control: Includes elements like Light Source, Lighting Environment, Shot Size (Framing), Camera Angle, Lens, and Camera Movement. For common cinematic terms, please refer to the Prompt Dictionary below.
Stylization: Describes the visual style of the scene, such as "Cyberpunk," "Line-drawing illustration," or "Post-apocalyptic style." See the Prompt Bank below for common styling examples.

🖼️ Image-to-Video Formula

Since the source image already establishes the subject, scene, and style, the prompt for video generation should focus on describing the desired motion and camera movement.

Formula: Prompt = Motion Description + Camera Movement

Components:

Motion Description: Describe the motion of elements in your image (e.g., people, animals), giving examples like "running" or "waving hello." Use adverbs such as "quickly" or "slowly" to control the pace and intensity of the action.
Camera Movement: Specific camera motion requirements can be controlled using prompts like "dolly in" or "pan left." If you wish for the camera to remain still, emphasize this with "static shot" or "fixed shot."

🎬 Cinema-Grade Aesthetic Control

Enhance the controllability and expressive quality of generated videos by crafting prompts that target different dimensions. A list of common dimensions with sample prompts has been prepared for reference. Explore and discover even more creative techniques!

Control Categories:

☑️ Prompt Recipe

Basic Formula
Advanced Formula
Image-to-Video Formula

☑️ Cinema-Grade Aesthetic Control

Light Source - Control the direction and type of lighting
Lighting Type - Choose between natural, artificial, or mixed lighting
Time of Day - Specify morning, noon, evening, or night
Shot Size - Control framing from extreme close-up to wide shot
Composition - Apply rule of thirds, leading lines, or other compositional techniques
Lens - Choose lens types and focal lengths for desired effects
Color Tone - Control the overall color palette and mood

☑️ Dynamic Control

Motion - Control the speed and type of movement
Character Emotion - Specify emotional states and expressions
Basic Camera Movement - Pan, tilt, zoom, and dolly movements
Advanced Camera Movement - Complex camera choreography and tracking shots

✏️ Stylization

Visual Style - Choose artistic styles like anime, realistic, or abstract
Visual Effects - Add special effects like lens flares, motion blur, or color grading

Tips for Success

Start Simple: Begin with the Basic Formula if you're new to AI video generation
Be Specific: Use detailed descriptions in the Advanced Formula for better results
Experiment: Try different combinations of aesthetic controls and stylization
Reference Real Cinema: Use established cinematography terms for professional results
Iterate: Generate multiple versions and refine your prompts based on results

This guide is designed to help you create stunning AI-generated videos with Wan 2.2's advanced capabilities. Experiment with different formulas and controls to discover your unique creative style!

AI Video Generation Guide - Wan 2.2

Easy Creation with One Click - AI Videos

Major Upgrade Announcement

Wan 2.2 Gets a Major Upgrade: More Beautiful and Fluid Video Generation!

🚀 Key Features

🎨 Cinema-Grade Aesthetic Control

🎭 Greatly Improved Complex Motion Generation

🌍 Enhanced Real-World Replication

📝 Prompt Recipe Guide

🟢 Basic Formula

For new users trying AI video for the first time or seeking creative inspiration: Simple, open-ended prompts can generate more imaginative videos.

Formula: Prompt = Subject + Scene + Motion

Components:

Subject: The main focus of the video, which can be a person, animal, plant, object, or an imagined entity that may not physically exist.
Scene: The environment where the subject is situated, including background and foreground. It can be a real physical space or an imagined fictional setting.
Motion: This includes both the subject's specific movements and the general motion within the scene. It can range from stillness, subtle movements, and partial motions to large-scale or overall dynamic action.

🔵 Advanced Formula

For users with some experience in AI video creation: Adding richer, more detailed descriptions to the basic formula enhances video quality, vividness, and storytelling.

Formula: Prompt = Subject (Subject Description) + Scene (Scene Description) + Motion (Motion Description) + Aesthetic Control + Stylization

Components:

Subject Description: Details about the subject's appearance, described using adjectives or short phrases.
- Examples: "A black-haired Miao girl wearing ethnic minority clothing" or "A flying fairy from another world, dressed in tattered yet elegant attire, with a pair of strange wings made of rubble fragments."
Scene Description: Details about the environment where the subject is located, described using adjectives or short phrases.
Motion Description: Describes the characteristics of movement, including amplitude, speed, and effects of the motion.
- Examples: "Violently swaying," "Slowly moving," or "Shattering glass."
Aesthetic Control: Includes elements like Light Source, Lighting Environment, Shot Size (Framing), Camera Angle, Lens, and Camera Movement. For common cinematic terms, please refer to the Prompt Dictionary below.
Stylization: Describes the visual style of the scene, such as "Cyberpunk," "Line-drawing illustration," or "Post-apocalyptic style." See the Prompt Bank below for common styling examples.

🖼️ Image-to-Video Formula

Since the source image already establishes the subject, scene, and style, the prompt for video generation should focus on describing the desired motion and camera movement.

Formula: Prompt = Motion Description + Camera Movement

Components:

Motion Description: Describe the motion of elements in your image (e.g., people, animals), giving examples like "running" or "waving hello." Use adverbs such as "quickly" or "slowly" to control the pace and intensity of the action.
Camera Movement: Specific camera motion requirements can be controlled using prompts like "dolly in" or "pan left." If you wish for the camera to remain still, emphasize this with "static shot" or "fixed shot."

🎬 Cinema-Grade Aesthetic Control

Control Categories:

☑️ Prompt Recipe

Basic Formula
Advanced Formula
Image-to-Video Formula

☑️ Cinema-Grade Aesthetic Control

Light Source - Control the direction and type of lighting
Lighting Type - Choose between natural, artificial, or mixed lighting
Time of Day - Specify morning, noon, evening, or night
Shot Size - Control framing from extreme close-up to wide shot
Composition - Apply rule of thirds, leading lines, or other compositional techniques
Lens - Choose lens types and focal lengths for desired effects
Color Tone - Control the overall color palette and mood

☑️ Dynamic Control

Motion - Control the speed and type of movement
Character Emotion - Specify emotional states and expressions
Basic Camera Movement - Pan, tilt, zoom, and dolly movements
Advanced Camera Movement - Complex camera choreography and tracking shots

✏️ Stylization

Visual Style - Choose artistic styles like anime, realistic, or abstract
Visual Effects - Add special effects like lens flares, motion blur, or color grading

Tips for Success

Start Simple: Begin with the Basic Formula if you're new to AI video generation
Be Specific: Use detailed descriptions in the Advanced Formula for better results
Experiment: Try different combinations of aesthetic controls and stylization
Reference Real Cinema: Use established cinematography terms for professional results
Iterate: Generate multiple versions and refine your prompts based on results

This guide is designed to help you create stunning AI-generated videos with Wan 2.2's advanced capabilities. Experiment with different formulas and controls to discover your unique creative style!