Veo3.1 Lite API

Lite
Image To Video
First Last Frame To Video

Endpoint: POST https://fal.run/fal-ai/veo3.1/lite Endpoint ID: fal-ai/veo3.1/lite

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/veo3.1/lite",
    arguments={
        "prompt": "A massive blue whale glides through crystal-clear deep ocean water, sunlight rays piercing through the surface above, bioluminescent plankton scattered around, cinematic slow motion"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

Examples

A ballerina performing an elegant pirouette on a moonlit outdoor stage. She wears a flowing white tutu that catches the silver light. Rose petals swirl around her in slow motion. The background is a dark forest with fireflies. Camera orbits slowly around her as she spins. Ethereal, dreamlike, cinema…

Input Schema

prompt

string

required

The text prompt describing the video you want to generate

aspect_ratio

AspectRatioEnum

default:"16:9"

Aspect ratio of the generated video Default value: "16:9"Possible values: 16:9, 9:16

duration

DurationEnum

default:"8s"

The duration of the generated video. Default value: "8s"Possible values: 4s, 6s, 8s

negative_prompt

string

A negative prompt to guide the video generation.

resolution

ResolutionEnum

default:"720p"

The resolution of the generated video. Default value: "720p"Possible values: 720p, 1080p

generate_audio

boolean

default:"true"

Whether to generate audio for the video. Default value: true

seed

integer

The seed for the random number generator.

auto_fix

boolean

default:"true"

Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. Default value: true

safety_tolerance

SafetyToleranceEnum

default:"4"

The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. Default value: "4"Possible values: 1, 2, 3, 4, 5, 6

Output Schema

video

File

required

The generated video.

Input Example

{
  "prompt": "A massive blue whale glides through crystal-clear deep ocean water, sunlight rays piercing through the surface above, bioluminescent plankton scattered around, cinematic slow motion",
  "aspect_ratio": "16:9",
  "duration": "8s",
  "resolution": "720p",
  "generate_audio": true,
  "auto_fix": true,
  "safety_tolerance": "4"
}

Output Example

{
  "video": {
    "url": "https://v3b.fal.media/files/b/0a94683f/r4vLtNmFDi_qpglfEX_q9_0a7258527ac84509a0997639765f5c79.mp4"
  }
}

Endpoint: POST https://fal.run/fal-ai/veo3.1/lite/image-to-video Endpoint ID: fal-ai/veo3.1/lite/image-to-video

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/veo3.1/lite/image-to-video",
    arguments={
        "prompt": "The subject turns to face the camera and smiles warmly.",
        "image_url": "https://storage.googleapis.com/falserverless/example_inputs/veo3-i2v-input.png"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

Examples

Time-lapse of the city transitioning through the day. Shadows shift across buildings, traffic flows in streaks of light, clouds race across the sky. The scene shifts from bright midday to warm golden hour. Smooth hyperlapse feel.

Input Schema

prompt

string

required

The text prompt describing how the image should be animated

aspect_ratio

AspectRatioEnum

default:"auto"

The aspect ratio of the generated video. Default value: "auto"Possible values: auto, 16:9, 9:16

duration

DurationEnum

default:"8s"

The duration of the generated video. Default value: "8s"Possible values: 4s, 6s, 8s

negative_prompt

string

A negative prompt to guide the video generation.

resolution

ResolutionEnum

default:"720p"

The resolution of the generated video. Default value: "720p"Possible values: 720p, 1080p

generate_audio

boolean

default:"true"

Whether to generate audio for the video. Default value: true

seed

integer

The seed for the random number generator.

auto_fix

boolean

default:"false"

Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them.

safety_tolerance

SafetyToleranceEnum

default:"4"

The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. Default value: "4"Possible values: 1, 2, 3, 4, 5, 6

image_url

string

required

URL of the input image to animate. Should be 720p or higher resolution in 16:9 or 9:16 aspect ratio.

Output Schema

video

File

required

The generated video.

Input Example

{
  "prompt": "The subject turns to face the camera and smiles warmly.",
  "aspect_ratio": "auto",
  "duration": "8s",
  "resolution": "720p",
  "generate_audio": true,
  "auto_fix": false,
  "safety_tolerance": "4",
  "image_url": "https://storage.googleapis.com/falserverless/example_inputs/veo3-i2v-input.png"
}

Output Example

{
  "video": {
    "url": "",
    "content_type": "image/png",
    "file_name": "z9RV14K95DvU.png",
    "file_size": 4404019
  }
}

Endpoint: POST https://fal.run/fal-ai/veo3.1/lite/first-last-frame-to-video Endpoint ID: fal-ai/veo3.1/lite/first-last-frame-to-video

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/veo3.1/lite/first-last-frame-to-video",
    arguments={
        "prompt": "A smooth transition between the two frames with natural motion.",
        "first_frame_url": "https://storage.googleapis.com/falserverless/example_inputs/veo31-flf2v-input-1.jpeg",
        "last_frame_url": "https://storage.googleapis.com/falserverless/example_inputs/veo31-flf2v-input-2.jpeg"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

Examples

The sun arcs across the sky from sunrise to sunset. Light transitions from cool dawn blue through warm golden midday to deep amber sunset. Shadows rotate and lengthen. Clouds drift and change shape. Smooth time-lapse feel.

Input Schema

prompt

string

required

The text prompt describing the video you want to generate

aspect_ratio

AspectRatioEnum

default:"auto"

The aspect ratio of the generated video. Default value: "auto"Possible values: auto, 16:9, 9:16

duration

string

default:"8s"

The duration of the generated video. Default value: "8s"

negative_prompt

string

A negative prompt to guide the video generation.

resolution

ResolutionEnum

default:"720p"

The resolution of the generated video. Default value: "720p"Possible values: 720p, 1080p

generate_audio

boolean

default:"true"

Whether to generate audio for the video. Default value: true

seed

integer

The seed for the random number generator.

auto_fix

boolean

default:"false"

Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them.

safety_tolerance

SafetyToleranceEnum

default:"4"

The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. Default value: "4"Possible values: 1, 2, 3, 4, 5, 6

first_frame_url

string

required

URL of the first frame of the video

last_frame_url

string

required

URL of the last frame of the video

Output Schema

video

File

required

The generated video.

Input Example

{
  "prompt": "A smooth transition between the two frames with natural motion.",
  "aspect_ratio": "auto",
  "duration": "8s",
  "resolution": "720p",
  "generate_audio": true,
  "auto_fix": false,
  "safety_tolerance": "4",
  "first_frame_url": "https://storage.googleapis.com/falserverless/example_inputs/veo31-flf2v-input-1.jpeg",
  "last_frame_url": "https://storage.googleapis.com/falserverless/example_inputs/veo31-flf2v-input-2.jpeg"
}

Output Example

{
  "video": {
    "url": "",
    "content_type": "image/png",
    "file_name": "z9RV14K95DvU.png",
    "file_size": 4404019
  }
}

Veo 3.1 — Video Generation
Veo 3.1 Fast — Video Generation
Veo3.1 Lite Image to Video — Video Generation
Veo3.1 Lite FLF — Video Generation
Veo3.1 Lite Text to Video — Video Generation

Limitations

aspect_ratio restricted to: 16:9, 9:16
duration restricted to: 4s, 6s, 8s
resolution restricted to: 720p, 1080p
safety_tolerance restricted to: 1, 2, 3, 4, 5, 6
aspect_ratio restricted to: auto, 16:9, 9:16

Video Generation

Image Generation

Audio

Vision

3D

Veo3.1 Lite API

Try it in the Playground

Quick Start

Examples

Input Schema

Output Schema

Input Example

Output Example

Try it in the Playground

Quick Start

Examples

Input Schema

Output Schema

Input Example

Output Example

Try it in the Playground

Quick Start

Examples

Input Schema

Output Schema

Input Example

Output Example

Limitations

Video Generation

Image Generation

Audio

Vision

3D

Try it in the Playground

​Quick Start

​Examples

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Examples

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Examples

​Input Schema

​Output Schema

​Input Example

​Output Example

​Related

​Limitations

Quick Start

Examples

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Examples

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Examples

Input Schema

Output Schema

Input Example

Output Example

Related

Limitations