• Picasso AI Logo
    Logo Picasso IA
  • Home
  • AI Image
    Nano Banana 2
  • AI Video
    Veo 3.1 Lite
  • 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 Video

Turn Text into Real-Time Video with LTX Video

LTX Video is a text-to-video model that generates 24 FPS clips at 768x512 resolution, producing footage faster than real-time playback speed. If you need video content for a project and you don't have footage or time to shoot it, this model turns a descriptive text prompt into a finished, watchable clip in seconds. You can describe a scene in detail and get back a clip with consistent motion, accurate framing, and a clear visual style. Drop in a reference image to anchor the first frame, and the model animates forward from that exact starting point. The model supports 13 aspect ratios from portrait 9:16 to ultrawide 21:9, so your output already matches your target format without any extra cropping. For content teams working on social video, marketers building quick campaign previews, or anyone who needs b-roll in a hurry, LTX Video fits directly into a production workflow. Write a detailed prompt, set your clip length and aspect ratio, and the video is ready before you expected. The longer and more specific your prompt, the closer the output gets to what you had in mind.

Lightricks

158k runs

Ltx Video

2024-11-29

Commercial Use

Turn Text into Real-Time Video with LTX Video

Table of contents

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

Overview

LTX Video is a text-to-video model that generates 24 FPS clips at 768x512 resolution faster than real-time playback. Describe a scene, pick your aspect ratio, and a finished video is ready in seconds on Picasso IA. It accepts both plain text prompts and an optional input image as the starting frame, giving you a concrete visual anchor for the generated motion. The model responds best to long, detailed descriptions, so the more specific your prompt, the sharper and more intentional the result.

How It Works

  • Write a detailed text prompt describing the scene, camera angle, lighting, and any movement you want in the video. The more specific the language, the more controlled the output.
  • Optionally upload an image to use as the first frame. This grounds the generated motion in a specific visual starting point and gives the model a color and composition reference.
  • Choose your aspect ratio from 13 options, from 9:16 for vertical social video to 21:9 for widescreen cinematic output.
  • Set the clip length in frames (97 to 257) and adjust the guidance scale to control how strictly the video follows your prompt.
  • Hit generate. The model renders your clip and makes it available for download, ready for standard video editing tools.

Frequently Asked Questions

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

Is it free to try? Yes, you can run the model without a paid account to start. Check the model page on Picasso IA for current free generation limits and available credits.

How long does it take to get results? LTX Video generates faster than real-time, so a 97-frame clip is usually ready in a few seconds. Longer clips and higher target resolutions add a bit more processing time.

What aspect ratios does it support? The model supports 13 aspect ratios, including 9:16 for vertical mobile content, 16:9 for standard video, 4:3 for traditional formats, and 21:9 for ultrawide cinematic output.

Can I use my own image as the starting frame? Yes. Upload any image through the image input field and the model uses it as the first frame, then generates the video motion from there. Use the image noise scale setting to control how closely the video stays tied to your original image.

What happens if the result doesn't look right? Rewrite your prompt to be longer and more specific, then try again. If the motion is too loose, increase the guidance scale. Changing the seed generates an entirely different output without touching any other setting.

Credit Cost

Each generation consumes 10 credits

10 credits

or 50 credits for 5 generations

Features

Everything this model can do for you

Real-time generation

Produces 24 FPS video clips faster than they can be played back.

Image-to-video support

Upload a reference image to anchor the first frame and animate forward from there.

13 aspect ratios

Output in any format from 9:16 portrait to 21:9 ultrawide without extra cropping.

Adjustable clip length

Choose between 97 and 257 frames to control the duration of your output.

Prompt-guided motion

Write detailed descriptions to shape camera movement, lighting, and scene content.

Negative prompt control

Specify what to exclude from the video to keep outputs clean and on target.

Reproducible results

Set a seed to regenerate the exact same video whenever you need it.

High-resolution outputs up to 1024px

Use Cases

Generate a short b-roll clip from a text description to fill gaps in a video edit

Animate a still photo by uploading it as the first frame and describing the motion you want

Create a looping background video for a presentation from a written scene description

Produce a scene preview for a film or commercial concept without shooting any footage

Turn a product description into a short video showing the item in a realistic setting

Generate atmospheric footage for social media posts by describing the mood, location, and action

Create a test clip to check how a scene concept reads visually before committing to a full production

Content creation for educational materials

Examples

16:9
13.1s
Cfg: 3
Steps: 30
Length: 97
Target Size: 640
low quality, worst quality, deformed, distorted, watermark

A man in a blue plaid shirt turns his head to look at a woman walking past in a red top. His expression is curious as he glances away from his companion in a light blue sleeveless top. The scene takes place on a busy city street with buildings and pedestrians visible in the background. The natural lighting suggests it's daytime. The camera captures the scene from street level, with the woman in red slightly out of focus in the foreground.

16:9
1m 25s
Cfg: 3
Steps: 30
Length: 97
Target Size: 640
low quality, worst quality, deformed, distorted, watermark

A chef prepares food in a professional kitchen. He has olive skin and dark, close-cropped hair, wearing traditional white chef's attire. Steam rises from the pan he's working with. The kitchen's stainless steel surfaces reflect the bright overhead lighting. The camera follows his hands as he cooks. The scene appears to be real-life footage.

16:9
11.8s
Cfg: 3
Steps: 30
Length: 97
Target Size: 640
low quality, worst quality, deformed, distorted, watermark

A woman with long brown hair and light skin smiles at another woman with long blonde hair. The woman with brown hair wears a black jacket and has a small, barely noticeable mole on her right cheek. The camera angle is a close-up, focused on the woman with brown hair's face. The lighting is warm and natural, likely from the setting sun, casting a soft glow on the scene. The scene appears to be real-life footage.

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