• Picasso AI Logo
    Logo Picasso IA
  • Home
  • AI Image
    Nano Banana 2
  • AI Video
    Veo 3.1 Fast
  • AI Chat
    Gemini 3 Pro
  • Edit Images
  • Upscale Image
  • Remove Background
  • Text to Speech
  • Effects
    NEW
  • Generations
  • Billing
  • Support
  • Account
  1. Collection
  2. Text to Video
  3. Ltx 2 Fast

Turn Text into Video Instantly with Ltx 2 Fast

Ltx 2 Fast is a text-to-video model built for speed. You type a description, and within seconds you get a video clip at up to 4K resolution. It also accepts a reference image as the first frame, so you can animate existing photos or product shots without extra tools. The model supports video lengths from 6 to 20 seconds, giving you enough room for social clips, short ads, or preview animations. At 1080p any duration is available, and 2K or 4K output is accessible for clips over 10 seconds. Audio generation is built in, so the output arrives with synchronized sound rather than silent footage. Ltx 2 Fast fits neatly into rapid production cycles. Shoot a product photo, feed it to the model with a short description, and have a shareable video draft in under a minute. Open Picasso IA, set your resolution, and generate on the first try.

Official

Lightricks

73.4k runs

Ltx 2 Fast

2025-10-22

Commercial Use

Table of contents

  • Overview
  • How It Works
  • Frequently Asked Questions
  • Credit Cost
  • Features
  • Use Cases
  • Examples
Get Nano Banana Pro

Overview

Ltx 2 Fast converts a text prompt, or a reference image, into a short video clip fast enough to fit into an active brainstorming session. Most text-to-video tools ask you to wait minutes for a result; this one delivers previews in seconds, so you can try five directions in the time others allow for one. On Picasso IA, you choose a duration from 6 to 20 seconds, pick the resolution that fits your target platform, and get a watchable clip without any technical setup. It suits creators who need real-time feedback on motion, pacing, and visual style before locking in a final version.

How It Works

  • Write a text prompt describing the scene, movement, and mood you want, or upload a still image to use as the opening frame of the video.
  • Select a clip duration between 6 and 20 seconds. Clips longer than 10 seconds are only available at 1080p resolution or higher.
  • Pick an output resolution: 1080p for standard delivery, 2K or 4K when sharpness matters more than speed.
  • Choose whether to include auto-generated audio, a sound layer built to match the video content, or turn it off for a silent clip.
  • Submit the job and receive a finished video file you can preview, download, and take straight into your editing timeline.

Frequently Asked Questions

Do I need programming skills or technical knowledge to use this? No, just open Ltx 2 Fast on Picasso IA, adjust the settings you want, and hit generate.

Is it free to try? Yes. You can run Ltx 2 Fast without a paid subscription to test the output quality and speed before committing to a plan.

How long does it take to get results? Generation times vary with clip length and resolution, but the model is built for speed. A 6-second 1080p clip typically returns in a few seconds, making it practical for real-time creative sessions.

What output formats are supported? The model returns a standard video file you can play in any modern media player or drag directly into editing software. No conversion step is needed before you use it.

Can I customize the output quality or style? Yes. You control duration (6 to 20 seconds), resolution (1080p, 2K, or 4K), and whether audio is generated. For image-to-video, the first frame shapes the visual style of the entire clip.

How many times can I run the model? You can run the model as many times as you like. Each iteration costs one generation credit, and you can adjust your prompt or settings between runs to home in on the result you want.

Where can I use the outputs? The resulting video files have no watermarks and can be used in social media posts, client presentations, ads, or any other project you have in mind.

Credit Cost

Each generation consumes 48 credits

48 credits

or 240 credits for 5 generations

Features

Everything this model can do for you

Text-to-video generation

Write a prompt and receive a finished video clip in seconds.

Image-to-video animation

Use a still photo as the first frame and the model fills in the motion.

Up to 4K resolution

Output at 1080p, 2K, or 4K to match the display format you need.

Variable video duration

Set clip length from 6 to 20 seconds depending on the project.

Built-in audio

Audio generates automatically alongside the video for a ready-to-play file.

No coding required

Adjust every setting through a simple interface with no technical setup.

Fast rendering

Clips generate quickly, letting you run multiple rounds of iteration in a short session.

Use Cases

Generate a short promotional video clip from a written product description in seconds

Animate a still product photo into a dynamic video by providing a brief text prompt

Create instant draft videos to share with clients for quick feedback and approval

Produce 4K video content from a text prompt for high-resolution display campaigns

Build rough storyboard animatics by describing each scene in plain text and animating it

Generate looping background videos for presentations by describing the desired motion and style

Create social media clips by converting a static photo into a 6-second animated video

Examples

Input
Input 1
Output
A high-speed drone shot captures a surreal scene in a dimly lit subway station, where a woman is flying effortlessly above the ground. She is wearing a flowing, traditional garment with red floral patterns, which billows dramatically around her. Her long, dark hair streams back in the wind, mirroring the rapid forward motion. The camera tracks her from the front, aligned perfectly to her unwavering, determined gaze. The background streaks past in a blur, with tiled walls and structural pillars creating a tunnel-like effect. Fluorescent lights overhead provide a stark, linear illumination, casting moving shadows across her face and highlighting the movement. The platform edges, outlined by fluorescent yellow safety lines, zip by beneath her, while distant, indistinct passengers and signs add to the vivid sense of speed and direction. The shot maintains the woman’s steady, surreal flight through the bustling transit space, creating an atmosphere of dynamic elegance and otherworldly grace. She yells: "LTX 2 now on Replicate. Try it today!"
40.2s
View Example
Input
Input 1
Output
A medium shot shows a small, fluffy monster with purple, pink, and blue fur standing in a forest clearing, initially facing the camera. The monster has two small, ridged horns and large, innocent-looking blue eyes. The forest floor is covered with brown leaves and patches of green moss. The monster begins to walk forward with a happy, bouncy gait, its fur jiggling with each step. As it walks, its eyes sparkle with joy, and a wide smile spreads across its face. The camera tracks the monster’s movement, keeping it centered in the frame as it continues its happy walk through the forest. The trees in the background sway gently in the breeze, and sunlight filters through the leaves, creating dappled shadows on the forest floor. The monster continues walking happily, its small feet padding softly on the ground, until it exits the frame on the right.
38.2s
View Example
Input
Input 1
Output
A medium shot focuses on the upper body of an old lighthouse guard with grey hair and a beard, wearing a dark jacket and a black turtleneck sweater. He stands on a grassy area in front of a white lighthouse that features a red top. The scene is set on a rainy day, with raindrops visibly falling. The man turns around and walks away slowly, showing him from behind standing on the edge of a cliff in front of the stormy ocean.
36.6s
View Example
Input
Input 1
Output
A man in a burgundy suit leans over an open car trunk at sunset, his intense eyes locked on the viewer. Slowly, he reaches inside with one hand and pulls out a water bottle, the bright plastic surface contrasts greatly with the surroundings. His other hand presses firmly on the edge of the trunk as he straightens his posture, exuding calm menace. After a tense pause, he lowers his gaze, then slams the trunk shut with deliberate force, the camera catching the sharp motion and the final echo of the closing lid. The atmosphere is cinematic, suspenseful, with the glowing diner sign in the background contrasting the darkness of the act.
36.1s
View Example
Input
Input 1
Output
"In a tender cinematic moment, a young boy stands quietly by a rain-speckled window, his face lit by the glow of fireworks bursting in the evening sky. The camera lingers on his thoughtful profile as colorful explosions of red, green, and gold reflect faintly across the glass. Outside, the celebration feels distant, while inside, his stillness conveys both wonder and melancholy, capturing the quiet contrast between noise and solitude."
35.7s
View Example
The video depicts a winding mountain road covered in snow, with a single vehicle traveling along it. The road is flanked by steep, rocky cliffs and sparse vegetation. The landscape is characterized by rugged terrain and a river visible in the distance. The scene captures the solitude and beauty of a winter drive through a mountainous region
34.5s
View Example
Input
Input 1
Output
A high-speed drone shot captures a surreal scene in a dimly lit subway station, where a woman is flying effortlessly above the ground. She is wearing a flowing, traditional garment with red floral patterns, which billows dramatically around her. Her long, dark hair streams back in the wind, mirroring the rapid forward motion. The camera tracks her from the front, aligned perfectly to her unwavering, determined gaze. The background streaks past in a blur, with tiled walls and structural pillars creating a tunnel-like effect. Fluorescent lights overhead provide a stark, linear illumination, casting moving shadows across her face and highlighting the movement. The platform edges, outlined by fluorescent yellow safety lines, zip by beneath her, while distant, indistinct passengers and signs add to the vivid sense of speed and direction. The shot maintains the woman’s steady, surreal flight through the bustling transit space, creating an atmosphere of dynamic elegance and otherworldly grace.
35.8s
View Example

Switch Category

Effects

Text To Image

Text To Image

Text To Video

Large Language Models

Large Language Models

Text To Speech

Text To Speech

Super Resolution

Super Resolution

Lipsync

AI Music Generation

AI Music Generation

Video Editing

Speech To Text

Speech To Text

AI Enhance Videos

Remove Backgrounds

Remove Backgrounds