fal.ai Text-to-Video Models

Quick Reference

When to Use This Skill

Use for text-to-video generation:

• Creating videos from text descriptions
• Choosing models by quality/​speed tier
• Crafting motion-oriented prompts
• Generating videos with native audio
• Preview workflow (fast) → Final (quality)

Related skills:

• For image-to-video: see fal-image-to-video
• For video editing: see fal-video-to-video
• For model comparison: see fal-model-guide

---

fal.ai Text-to-Video Models

Complete reference for all text-to-video generation models on fal.ai.

Kling Video Models

Kling 2.0 Standard

Endpoint: fal-ai/​kling-video/​v2.0/​text-to-video Best For: Good quality, cost-effective

import { fal } from "@fal-ai/​client";

const result = await fal.subscribe("fal-ai/​kling-video/​v2.0/​text-to-video", {
  input: {
    prompt: "A majestic eagle soaring over snow-capped mountains at golden hour, cinematic lighting",
    duration: "5",  // "5" or "10" seconds
    aspect_ratio: "16:9",
    negative_prompt: "blurry, distorted, low quality"
  }
});

console.log(result.video.url);

import fal_client

result = fal_client.subscribe(
    "fal-ai/​kling-video/​v2.0/​text-to-video",
    arguments={
        "prompt": "A majestic eagle soaring over mountains",
        "duration": "5",
        "aspect_ratio": "16:9",
        "negative_prompt": "blurry, distorted"
    }
)
print(result["video"]["url"])

Kling 2.5 Pro

Endpoint: fal-ai/​kling-video/​v2.5/​pro/​text-to-video Best For: Professional quality videos

const result = await fal.subscribe("fal-ai/​kling-video/​v2.5/​pro/​text-to-video", {
  input: {
    prompt: "A luxury car driving through a mountain road, drone shot, cinematic",
    duration: "5",
    aspect_ratio: "16:9",
    negative_prompt: "shaky, amateur, blurry"
  }
});

Kling 2.6 Pro (Latest)

Endpoint: fal-ai/​kling-video/​v2.6/​pro/​text-to-video Best For: Highest quality with native audio generation

The latest Kling model with built-in audio generation.

const result = await fal.subscribe("fal-ai/​kling-video/​v2.6/​pro/​text-to-video", {
  input: {
    prompt: "Ocean waves crashing on rocky cliffs at sunset, seagulls flying, ambient sounds",
    duration: "5",
    aspect_ratio: "16:9",
    negative_prompt: "static, boring, low quality"
  }
});

console.log(result.video.url);
console.log(result.audio?.url);  // Native audio included

Kling Parameters:

Sora 2

Sora (OpenAI)

Endpoint: fal-ai/​sora Best For: Advanced, creative video generation

const result = await fal.subscribe("fal-ai/​sora", {
  input: {
    prompt: "A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. She wears a black leather jacket, a long red dress, and black boots. She carries a black purse. She wears sunglasses and red lipstick. She walks confidently. The street is damp and reflective, creating a mirror effect of the colorful lights.",
    duration: 10,
    aspect_ratio: "16:9",
    resolution: "1080p"
  }
});

console.log(result.video.url);

Sora Parameters:

LTX Video Models

LTX Video (Original)

Endpoint: fal-ai/​ltx-video Best For: Fast, efficient generation

const result = await fal.subscribe("fal-ai/​ltx-video", {
  input: {
    prompt: "A beautiful sunset over the ocean with gentle waves",
    negative_prompt: "low quality, blurry, distorted",
    num_inference_steps: 30,
    guidance_scale: 7.5,
    aspect_ratio: "16:9"
  }
});

LTX Video v2

Endpoint: fal-ai/​ltx-video/​v2 Best For: Improved quality over v1

const result = await fal.subscribe("fal-ai/​ltx-video/​v2", {
  input: {
    prompt: "A futuristic city with flying cars and neon lights",
    negative_prompt: "ugly, distorted",
    num_inference_steps: 35,
    guidance_scale: 7.0,
    resolution: "720p"
  }
});

LTX-2 Pro

Endpoint: fal-ai/​ltx-2-pro Best For: High fidelity with audio support

const result = await fal.subscribe("fal-ai/​ltx-2-pro", {
  input: {
    prompt: "A jazz band performing in a dimly lit club, smooth music, intimate atmosphere",
    negative_prompt: "worst quality, inconsistent motion, blurry",
    num_inference_steps: 30,
    guidance_scale: 3.5,
    resolution: "720p",
    enable_audio: true  // Generate matching audio
  }
});

console.log(result.video.url);
console.log(result.audio?.url);  // Audio track if enabled

LTX Parameters:

Wan Video

Wan v2.1 1.3B

Endpoint: fal-ai/​wan/​v2.1/​1.3b/​text-to-video Best For: Lightweight, fast generation

const result = await fal.subscribe("fal-ai/​wan/​v2.1/​1.3b/​text-to-video", {
  input: {
    prompt: "A cat playing with a ball of yarn, cute, playful",
    num_frames: 81,  // Number of frames
    resolution: "480p"
  }
});

Wan v2.1 14B

Endpoint: fal-ai/​wan/​v2.1/​14b/​text-to-video Best For: Higher quality, larger model

const result = await fal.subscribe("fal-ai/​wan/​v2.1/​14b/​text-to-video", {
  input: {
    prompt: "A professional chef preparing sushi, precise movements, high-end restaurant",
    num_frames: 81,
    resolution: "720p"
  }
});

MiniMax Video

MiniMax Text-to-Video

Endpoint: fal-ai/​minimax-video/​text-to-video Best For: Balanced quality and speed

const result = await fal.subscribe("fal-ai/​minimax-video/​text-to-video", {
  input: {
    prompt: "A butterfly emerging from a cocoon, macro shot, nature documentary style",
    prompt_optimizer: true  // Enhance prompt automatically
  }
});

MiniMax Parameters:

Runway Gen-3

Runway Gen-3 Turbo

Endpoint: fal-ai/​runway-gen3/​turbo/​text-to-video Best For: Fast iteration, previews

const result = await fal.subscribe("fal-ai/​runway-gen3/​turbo/​text-to-video", {
  input: {
    prompt: "A dancer performing ballet in an empty theater, spotlight, graceful movements",
    duration: 5,
    ratio: "16:9"
  }
});

Runway Parameters:

Luma Dream Machine

Luma Text-to-Video

Endpoint: fal-ai/​luma-dream-machine Best For: Creative, artistic videos

const result = await fal.subscribe("fal-ai/​luma-dream-machine", {
  input: {
    prompt: "A magical forest with glowing mushrooms and fireflies at night",
    aspect_ratio: "16:9",
    loop: false
  }
});

Luma Parameters:

CogVideoX

CogVideoX Text-to-Video

Endpoint: fal-ai/​cogvideox Best For: Open-source alternative

const result = await fal.subscribe("fal-ai/​cogvideox", {
  input: {
    prompt: "A timelapse of a flower blooming, from bud to full bloom",
    num_inference_steps: 50,
    guidance_scale: 6.0
  }
});

CogVideoX-5B

Endpoint: fal-ai/​cogvideox-5b Best For: Higher quality open-source

const result = await fal.subscribe("fal-ai/​cogvideox-5b", {
  input: {
    prompt: "An astronaut floating in space with Earth in the background",
    num_inference_steps: 50,
    guidance_scale: 6.0,
    num_frames: 49
  }
});

HunyuanVideo

Hunyuan Video

Endpoint: fal-ai/​hunyuan-video Best For: Chinese model, good quality

const result = await fal.subscribe("fal-ai/​hunyuan-video", {
  input: {
    prompt: "A traditional Chinese dragon dance during festival celebration",
    num_inference_steps: 50,
    guidance_scale: 6.0
  }
});

Model Comparison

Quality Rankings

Feature Comparison

Speed Comparison (approximate)

Prompt Engineering for Video

Structure Your Prompts

[Subject] + [Action] + [Setting] + [Style] + [Camera/​Technical]

Examples:

// Good: Specific, action-oriented
"A golden retriever running through autumn leaves in a forest, slow motion, cinematic, warm lighting, tracking shot"

// Bad: Vague, static
"A dog in a forest"

Motion Keywords

Style Keywords

Camera Movements

Complete Parameter Reference

interface TextToVideoInput {
  // Required
  prompt: string;

  // Duration (varies by model)
  duration?: number | string;  // seconds

  // Dimensions
  aspect_ratio?: "16:9" | "9:16" | "1:1" | "4:3" | "21:9";
  resolution?: "480p" | "720p" | "1080p";

  // Quality control
  negative_prompt?: string;
  num_inference_steps?: number;
  guidance_scale?: number;

  // Reproducibility
  seed?: number;

  // Model-specific
  prompt_optimizer?: boolean;  // MiniMax
  enable_audio?: boolean;      // LTX-2 Pro, Kling 2.6
  loop?: boolean;              // Luma
  num_frames?: number;         // Wan, CogVideoX
}

Workflow Examples

Production Workflow

// 1. Fast preview with Runway Turbo
const preview = await fal.subscribe("fal-ai/​runway-gen3/​turbo/​text-to-video", {
  input: {
    prompt: "A woman walking through a rainy city street at night",
    duration: 5,
    ratio: "16:9"
  }
});

console.log("Preview:", preview.video.url);
// Review and refine prompt...

// 2. Final render with Kling Pro
const final = await fal.subscribe("fal-ai/​kling-video/​v2.6/​pro/​text-to-video", {
  input: {
    prompt: "A stylish woman walking confidently through a rainy Tokyo street at night, neon reflections on wet pavement, cinematic lighting, slow motion, tracking shot",
    duration: "10",
    aspect_ratio: "16:9"
  }
});

console.log("Final:", final.video.url);

Batch Generation

const prompts = [
  "A sunrise over mountains",
  "A sunset over the ocean",
  "A storm rolling in"
];

const videos = await Promise.all(
  prompts.map(prompt =>
    fal.subscribe("fal-ai/​ltx-video", {
      input: { prompt, aspect_ratio: "16:9" }
    })
  )
);

videos.forEach((v, i) => console.log(`Video ${i + 1}: ${v.video.url}`));

Best Practices

1. Use subscribe() not run() - Video generation takes time
2. Start with previews - Use faster models to iterate on prompts
3. Be specific about motion - Describe what moves and how
4. Include camera direction - Guide the visual perspective
5. Use negative prompts - Avoid common artifacts
6. Match model to need - Don't use premium for tests
7. Include audio keywords - For models that support audio generation