Text, image, and references to video

AI Video Models Production-ready video generation APIs

Build with the latest AI video models on fal. Generate production-ready video from text, images, and references through fast, scalable APIs.

Latest models

Choose the right video model for your workflow

Compare current video generation models from leading providers, selected from the active fal catalog.

MiniMax H3 Max Text to Video
Minimax logo
minimax/h3-max/text-to-video
text-to-video

fal's H3 Max is a post-trained variant of MiniMax H3, tuned for stronger prompt adherence and better aesthetics while co-optimized with our custom inference stack for higher throughput with no compromises on output quality

stylizedtransformlipsync
H3 Max Reference to Video
Minimax logo
minimax/h3-max/reference-to-video
image-to-video

fal's H3 Max is a post-trained variant of MiniMax H3, tuned for stronger prompt adherence and better aesthetics while co-optimized with our custom inference stack for higher throughput with no compromises on output quality

stylizedtransformtypography
Wan 3.0 Prime
Alibaba logo
alibaba/wan-3.0-prime/text-to-video
text-to-video

Wan 3.0 Prime Text-to-Video transforms written prompts into polished videos with accelerated generation, fluid motion, strong scene fidelity, and coherent visual storytelling. Built for fast creative iteration, it brings complex ideas to life while preserving visual detail and cinematic consistency throughout each shot.

textvideo
Wan Text to Video
Alibaba logo
alibaba/wan-3.0/text-to-video
text-to-video

Wan 3.0 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.

stylizedtransformlipsync
Kling Video V3 Turbo Pro Text to Video
Kling logo
fal-ai/kling-video/v3/turbo/pro/text-to-video
text-to-video

Generate high quality 1080p videos using Kling's Turbo 3.0 model, with improved lipsync and multishot generation capabilities.

klingv31080p
Kling Video V3 Text to Video 4K
Kling logo
fal-ai/kling-video/v3/4k/text-to-video
text-to-video

Kling's Native 4K is a video generation model that directly outputs professional-grade 4K video in one step, eliminating the need for post-production upscaling

stylizedtransformlipsync
PixVerse C1 Text To Video
Pixverse logo
fal-ai/pixverse/c1/text-to-video
text-to-video

Generate film-grade videos from text prompts with native audio, up to 1080p and 15 seconds, using PixVerse C1.

video-generationtext-to-videopixverse
Veo 3.1
Google logo
fal-ai/veo3.1
text-to-video

Veo 3.1 by Google, the most advanced AI video generation model in the world. With sound on!

Wan 3.0
Alibaba logo
alibaba/wan-3.0/image-to-video
image-to-video

Wan 3.0 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.

stylizedtransformlipsync
Mirage Avatar X
mirage-api/avatar-x/reference-to-video
image-to-video

The Avatar X API offers access to Mirage's most advanced generation model yet, delivering industry-leading identity preservation and expressivity in AI video

avatarlipsynctalking-head
Kling Video V3 Turbo Pro Image to Video
Kling logo
fal-ai/kling-video/v3/turbo/pro/image-to-video
image-to-video

Generate high quality 1080p videos from images using Kling's Turbo 3.0 model, with improved lipsync and multishot generation capabilities.

klingv3turbo
Flux 3 Image to Video
Black Forest Labs logo
blackforestlabs/flux-3/keyframes-to-video
image-to-video

FLUX 3 is Black Forest Labs' frontier video model. This endpoint builds video from a sequence of keyframes, generating the motion between each anchor point for precise control over how a shot progresses.

stylizedtransformlipsync
PixVerse C1 Image To Video
Pixverse logo
fal-ai/pixverse/c1/image-to-video
image-to-video

Animate images into cinematic videos with PixVerse C1, supporting 1080p resolution and native audio generation.

video-generationimage-to-videopixverse
Veo 3.1
Google logo
fal-ai/veo3.1/image-to-video
image-to-video

Veo 3.1 is the latest state-of-the art video generation model from Google DeepMind

How it works

From an idea to a production video

Use the playground for a quick test or call the same model from your application through the API.

01Choose a workflowStart from a text prompt, an image, or multiple visual references. Pick the endpoint that matches your source material and production requirements.
02Direct the generationDescribe the scene, action, camera movement, and sound. Configure duration, aspect ratio, resolution, and model-specific controls in the playground.
03Integrate the APIReview the generated clip, then call the same hosted endpoint from your application with the fal client or HTTP API.
Examples

See what the latest AI video models can create

Explore generations from the featured models, then open an example to inspect its inputs and run it yourself.

Create a **Flappy Bird-style pixel-art gameplay animation set entirely in San Francisco**, presented as authentic retro mobile game footage.

A tiny pixel-art bird automatically flies from left to right while the camera remains fixed in a classic side-scrolling 2D perspective. The player keeps the bird airborne by repeatedly flapping upward while gravity constantly pulls it downward.

Instead of the traditional green pipes, every obstacle should be unmistakably **San Francisco-themed** while preserving the exact same simple gameplay mechanic: each obstacle creates a narrow vertical opening that the bird must fly through without touching anything.

Use obstacles such as:

* Two steep San Francisco hills forming a narrow gap.
* Victorian houses extending down from above and up from below.
* Giant red sections of the Golden Gate Bridge creating openings between the towers and roadway.
* Cable cars entering from the top and bottom of the screen.
* Downtown skyscrapers forming tight passages.
* The Transamerica Pyramid extending into the flight path.
* Coastal cliffs surrounding a narrow opening.
* Construction scaffolding creating rectangular gaps.
* Giant redwood trees framing the flight path.
* Fog banks partially surrounding openings while keeping the playable gap clearly visible.

Every obstacle must function like a real Flappy Bird obstacle: **one clear opening, one required flight path, no alternate routes.**

### SAN FRANCISCO ENVIRONMENT

Make the scrolling background unmistakably San Francisco.

Include layered pixel-art scenery:

**Foreground:** rooftops, streetlights, cable-car wires, fire escapes, trees, signs and passing architectural details.

**Midground:** colorful Victorian houses, steep streets, cable cars, cafés, parks, dense neighborhoods and downtown buildings.

**Background:** San Francisco Bay, Alcatraz, the Transamerica Pyramid, Salesforce Tower, rolling hills and the Golden Gate Bridge.

**Sky:** bright California sunset colors, huge pixel clouds, drifting coastal fog, distant birds and subtle atmospheric animation.

The scenery should continuously scroll from right to left while the bird remains around the left-center of the screen.

### GAMEPLAY

The bird flies automatically forward.

Each flap causes a quick upward movement followed by a smooth downward arc from gravity.

The gameplay should be fast, simple and immediately readable.

Show the bird successfully passing through multiple increasingly difficult San Francisco-themed gaps.

Obstacle spacing should feel fair but challenging.

Never allow the bird to fly around an obstacle. Every obstacle must extend completely from either the top or bottom edge of the playable screen, leaving only one intentional opening.

The sequence should feel like genuine uninterrupted gameplay rather than a cinematic animation.

### BIRD ANIMATION

Use a charming, simple pixel-art bird with a tiny 2–4 frame wing-flapping animation.

Keep the bird's:

* sprite design
* proportions
* colors
* beak
* wings
* eyes

completely consistent throughout the sequence.

When flapping upward, slightly tilt the bird upward.

When falling, gradually tilt the bird downward.

### SCORE

Include a large retro pixel-number score centered near the top of the screen.

Start at a low score and visibly increase it by one every time the bird successfully clears an obstacle:

**3 → 4 → 5 → 6 → 7**

Keep the UI extremely minimal.

No menus, dialogue, instructions or unnecessary interface elements.

### PIXEL-ART STYLE

Crisp handcrafted pixel art with visible individual pixels.

Limited retro color palette.

No 3D rendering.

No realistic textures.

No vector graphics.

No motion blur.

No anti-aliasing.

No smooth painted edges.

Everything should look intentionally created as pixel art.

The visual quality should feel like a beautifully polished modern indie recreation of a classic 2010s mobile game.

### CAMERA

Classic fixed side-view gameplay camera.

No zoom.

No camera rotation.

No cuts.

No cinematic angles.

The bird maintains approximately the same horizontal position while the entire San Francisco environment continuously scrolls from right to left.

### AUDIO

Use a simple catchy retro mobile-game soundtrack with light chiptune melodies.

Add:

* short flap sound on every wing beat
* satisfying point sound whenever an obstacle is cleared
* subtle cable-car bell sounds
* distant city ambience
* occasional seagulls
* soft wind near the Bay

Keep the music playful and addictive.

### OVERALL FEEL

It should immediately read as:

**“Flappy Bird, but the entire game takes place in San Francisco.”**

Simple, addictive, funny and instantly recognizable.

The city's architecture and landmarks should replace the traditional obstacle design without making the gameplay complicated.

**Format:** 16:9 widescreen, continuous side-scrolling pixel-art gameplay, fixed camera, no cuts, retro game audio, minimal score HUD, no logos.

Create a **Flappy Bird-style pixel-art gameplay animation set entirely in San Francisco**, presented as authentic retro mobile game footage. A tiny pixel-art bird automatically flies from left to right while the camera remains fixed in a classic side-scrolling 2D perspective. The player keeps the bird airborne by repeatedly flapping upward while gravity constantly pulls it downward. Instead of the traditional green pipes, every obstacle should be unmistakably **San Francisco-themed** while preserving the exact same simple gameplay mechanic: each obstacle creates a narrow vertical opening that the bird must fly through without touching anything. Use obstacles such as: * Two steep San Francisco hills forming a narrow gap. * Victorian houses extending down from above and up from below. * Giant red sections of the Golden Gate Bridge creating openings between the towers and roadway. * Cable cars entering from the top and bottom of the screen. * Downtown skyscrapers forming tight passages. * The Transamerica Pyramid extending into the flight path. * Coastal cliffs surrounding a narrow opening. * Construction scaffolding creating rectangular gaps. * Giant redwood trees framing the flight path. * Fog banks partially surrounding openings while keeping the playable gap clearly visible. Every obstacle must function like a real Flappy Bird obstacle: **one clear opening, one required flight path, no alternate routes.** ### SAN FRANCISCO ENVIRONMENT Make the scrolling background unmistakably San Francisco. Include layered pixel-art scenery: **Foreground:** rooftops, streetlights, cable-car wires, fire escapes, trees, signs and passing architectural details. **Midground:** colorful Victorian houses, steep streets, cable cars, cafés, parks, dense neighborhoods and downtown buildings. **Background:** San Francisco Bay, Alcatraz, the Transamerica Pyramid, Salesforce Tower, rolling hills and the Golden Gate Bridge. **Sky:** bright California sunset colors, huge pixel clouds, drifting coastal fog, distant birds and subtle atmospheric animation. The scenery should continuously scroll from right to left while the bird remains around the left-center of the screen. ### GAMEPLAY The bird flies automatically forward. Each flap causes a quick upward movement followed by a smooth downward arc from gravity. The gameplay should be fast, simple and immediately readable. Show the bird successfully passing through multiple increasingly difficult San Francisco-themed gaps. Obstacle spacing should feel fair but challenging. Never allow the bird to fly around an obstacle. Every obstacle must extend completely from either the top or bottom edge of the playable screen, leaving only one intentional opening. The sequence should feel like genuine uninterrupted gameplay rather than a cinematic animation. ### BIRD ANIMATION Use a charming, simple pixel-art bird with a tiny 2–4 frame wing-flapping animation. Keep the bird's: * sprite design * proportions * colors * beak * wings * eyes completely consistent throughout the sequence. When flapping upward, slightly tilt the bird upward. When falling, gradually tilt the bird downward. ### SCORE Include a large retro pixel-number score centered near the top of the screen. Start at a low score and visibly increase it by one every time the bird successfully clears an obstacle: **3 → 4 → 5 → 6 → 7** Keep the UI extremely minimal. No menus, dialogue, instructions or unnecessary interface elements. ### PIXEL-ART STYLE Crisp handcrafted pixel art with visible individual pixels. Limited retro color palette. No 3D rendering. No realistic textures. No vector graphics. No motion blur. No anti-aliasing. No smooth painted edges. Everything should look intentionally created as pixel art. The visual quality should feel like a beautifully polished modern indie recreation of a classic 2010s mobile game. ### CAMERA Classic fixed side-view gameplay camera. No zoom. No camera rotation. No cuts. No cinematic angles. The bird maintains approximately the same horizontal position while the entire San Francisco environment continuously scrolls from right to left. ### AUDIO Use a simple catchy retro mobile-game soundtrack with light chiptune melodies. Add: * short flap sound on every wing beat * satisfying point sound whenever an obstacle is cleared * subtle cable-car bell sounds * distant city ambience * occasional seagulls * soft wind near the Bay Keep the music playful and addictive. ### OVERALL FEEL It should immediately read as: **“Flappy Bird, but the entire game takes place in San Francisco.”** Simple, addictive, funny and instantly recognizable. The city's architecture and landmarks should replace the traditional obstacle design without making the gameplay complicated. **Format:** 16:9 widescreen, continuous side-scrolling pixel-art gameplay, fixed camera, no cuts, retro game audio, minimal score HUD, no logos.

aspect_ratio: 16:9
Customize it
5s Living Oil Painting | 16:9 | Impressionist Post-Painterly Texture | Sea-Cliff Wind and Scattering Blossoms

FIRST FRAME: strictly preserve the reference image's original composition, palette, and brushwork. Nothing is re-rendered as photoreal — the animation must look like an oil painting in motion, visible impasto strokes and palette-knife ridges holding their identity as they move.

SUBJECT: young dark-haired woman in a sage-olive long-sleeved blouse with a patterned sash, head tilted down and to her right, eyes lowered, expression calm and inward. Both bare forearms lift toward a great bundle of white chrysanthemum blooms breaking apart in the air before her. Face structure, hair mass, sleeve folds, and skin tone stay consistent throughout.

5s Living Oil Painting | 16:9 | Impressionist Post-Painterly Texture | Sea-Cliff Wind and Scattering Blossoms FIRST FRAME: strictly preserve the reference image's original composition, palette, and brushwork. Nothing is re-rendered as photoreal — the animation must look like an oil painting in motion, visible impasto strokes and palette-knife ridges holding their identity as they move. SUBJECT: young dark-haired woman in a sage-olive long-sleeved blouse with a patterned sash, head tilted down and to her right, eyes lowered, expression calm and inward. Both bare forearms lift toward a great bundle of white chrysanthemum blooms breaking apart in the air before her. Face structure, hair mass, sleeve folds, and skin tone stay consistent throughout.

aspect_ratio: adaptive
Customize it

Customize it
generated withfal-ai/veo3.1
Create a 5-second live-action Hollywood film shot in a bright university library. A thoughtful professor stands in a medium shot, turns slightly toward an unseen student, and calmly says, “What is the real?” Natural daylight, professional cinema camera, realistic performance, subtle camera drift, no close-up, no dark lighting, perfect lip sync.

Create a 5-second live-action Hollywood film shot in a bright university library. A thoughtful professor stands in a medium shot, turns slightly toward an unseen student, and calmly says, “What is the real?” Natural daylight, professional cinema camera, realistic performance, subtle camera drift, no close-up, no dark lighting, perfect lip sync.

aspect_ratio: 16:9
Customize it
He explodes upward out of the black. Both arms drive toward the falling apple, body twisting, white linen sleeves snapping taut then bunching as his shoulders roll. The apple tumbles fast, end over end, its stem whipping. He mistimes it — the fruit glances off his fingertips and spins away; he lunges after it, throwing his weight sideways, hair swinging across his face, eyes flashing wide. He catches it hard against his palm, the impact shoving his arm back and down, linen collapsing in loose folds. He pulls it in against his chest, breathing hard, and breaks into a grin as he looks straight into the lens. The candlelight jumps with every movement, flaring across his forearms and guttering into darkness behind him.

He explodes upward out of the black. Both arms drive toward the falling apple, body twisting, white linen sleeves snapping taut then bunching as his shoulders roll. The apple tumbles fast, end over end, its stem whipping. He mistimes it — the fruit glances off his fingertips and spins away; he lunges after it, throwing his weight sideways, hair swinging across his face, eyes flashing wide. He catches it hard against his palm, the impact shoving his arm back and down, linen collapsing in loose folds. He pulls it in against his chest, breathing hard, and breaks into a grin as he looks straight into the lens. The candlelight jumps with every movement, flaring across his forearms and guttering into darkness behind him.

aspect_ratio: 16:9
Customize it
minecraft creative mode but in real world. in new york city.

minecraft creative mode but in real world. in new york city.

aspect_ratio: 16:9
Customize it
Ultra-high-velocity anime action sequence, masterpiece quality. A tall woman knight with short pale-gold hair and calm luminous eyes, wearing weightless white-and-silver plate armor with a long drifting translucent cape, wielding a single ethereal longsword of pure white light. She fights alone against thirty enemy knights of a rival order — real warriors in charcoal-grey lacquered plate with crimson underlayers, tattered war-banners on their backs, bare faces and half-visors, armed with spears, twin curved blades, banner-polearms, greatswords, warhammers and lightning lances. They fight in disciplined formations, shouting orders and flanking her across a chain of shattered marble temple fragments floating high above an endless sea of clouds at dusk. She never stops moving — sprinting, sliding, vaulting, wall-running, leaping between islands, defeating each knight in one or two strikes without breaking stride, armor shearing, sparks bursting, banners cut, bodies falling away into the clouds behind her. Rain falls upward in the wind, aurora ribbons shimmer overhead, wet marble glows, volumetric god rays cut through the cloud sea. Relentless forward momentum, elegant lethal choreography, dynamic orbital camera chained to her shoulder, whip-pans, speed lines, energy waves, radiant sparks on every clash, marble debris and glowing dust drifting in slow arcs, dramatic close-ups on her calm luminous eyes and on the fear in theirs, cinematic lighting, anime movie quality, highly detailed backgrounds, ultra smooth fluid animation, breathtaking final attack

Ultra-high-velocity anime action sequence, masterpiece quality. A tall woman knight with short pale-gold hair and calm luminous eyes, wearing weightless white-and-silver plate armor with a long drifting translucent cape, wielding a single ethereal longsword of pure white light. She fights alone against thirty enemy knights of a rival order — real warriors in charcoal-grey lacquered plate with crimson underlayers, tattered war-banners on their backs, bare faces and half-visors, armed with spears, twin curved blades, banner-polearms, greatswords, warhammers and lightning lances. They fight in disciplined formations, shouting orders and flanking her across a chain of shattered marble temple fragments floating high above an endless sea of clouds at dusk. She never stops moving — sprinting, sliding, vaulting, wall-running, leaping between islands, defeating each knight in one or two strikes without breaking stride, armor shearing, sparks bursting, banners cut, bodies falling away into the clouds behind her. Rain falls upward in the wind, aurora ribbons shimmer overhead, wet marble glows, volumetric god rays cut through the cloud sea. Relentless forward momentum, elegant lethal choreography, dynamic orbital camera chained to her shoulder, whip-pans, speed lines, energy waves, radiant sparks on every clash, marble debris and glowing dust drifting in slow arcs, dramatic close-ups on her calm luminous eyes and on the fear in theirs, cinematic lighting, anime movie quality, highly detailed backgrounds, ultra smooth fluid animation, breathtaking final attack

aspect_ratio: adaptive
Customize it

Customize it
generated withfal-ai/veo3.1
The near man says flatly: "Did you hear about H3 Max?" A beat of silence,
wind moving across the lot. The far man's mouth pulls into a slow half-smile and he
answers, warm and certain: "Dude, I love it." The near man exhales and shakes his head
once, almost smiling. Native audio, lip-synced English dialogue, distant traffic hum,
wind. No music, no subtitles, no camera movement.

The near man says flatly: "Did you hear about H3 Max?" A beat of silence, wind moving across the lot. The far man's mouth pulls into a slow half-smile and he answers, warm and certain: "Dude, I love it." The near man exhales and shakes his head once, almost smiling. Native audio, lip-synced English dialogue, distant traffic hum, wind. No music, no subtitles, no camera movement.

aspect_ratio: adaptive
Customize it
Exactly 5 seconds. Inside a bright sterile laboratory, a cryogenic chamber opens and cold vapor spills across the floor. A confused man slowly sits up. A scientist steps forward and says, “Welcome back.” The man asks, “What year is it?” The scientist hesitates as the camera gently pulls backward. Photorealistic Hollywood science-fiction drama, soft white daylight, realistic vapor, restrained acting, accurate lip sync, no extreme close-up.

Exactly 5 seconds. Inside a bright sterile laboratory, a cryogenic chamber opens and cold vapor spills across the floor. A confused man slowly sits up. A scientist steps forward and says, “Welcome back.” The man asks, “What year is it?” The scientist hesitates as the camera gently pulls backward. Photorealistic Hollywood science-fiction drama, soft white daylight, realistic vapor, restrained acting, accurate lip sync, no extreme close-up.

aspect_ratio: 16:9
Customize it
Use Cases

What can you build with AI video models?

Generate and transform video without managing model infrastructure.

Film and storytelling

Turn concepts into moving scenes

Generate cinematic shots, storyboards, and visual sequences from scripts, prompts, and reference frames.

Marketing

Produce campaign video faster

Create social clips, product videos, and localized campaign variations without managing model infrastructure.

Creative tools

Build video generation into your product

Add text-to-video, image animation, reference-guided generation, and video utilities to automated workflows.

FAQ

Common questions about AI video models

Which AI video model should I choose?

Choose based on your input, output quality, speed, duration, audio, and control requirements. Open a featured model to compare its schema, pricing, and examples before integrating it.

Can these models generate video from text and images?

Yes. fal hosts text-to-video, image-to-video, reference-to-video, and keyframe-to-video endpoints. The supported inputs and controls vary by model.

Can I use AI video models through an API?

Yes. Every featured model has a hosted fal API and an interactive playground. Open a model to review its request schema, pricing, and code examples, or create an API key from your dashboard.

Do AI-generated videos include audio?

Some models generate synchronized audio natively, while others return silent video. Check the selected endpoint's schema and model description for its audio capabilities.

What video utilities are available?

fal provides hosted utilities for common post-processing tasks including trimming, scaling, blending, and reversing video. They can be composed with generation endpoints in a production workflow.