LTX Video
Neural Network
LTX Video is a real-time video generation model: 768x512 resolution at 24 fps.
Specifications
- Input
- text, images
- Output
- video
- Aspect ratio
- 1:1, 1:2, 2:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 9:21, 21:9
Video generation
(duration 8 sec., 720p)
Video generation
(duration 8 sec., 1080p)
How it works LTX Video?
LTX Video is a generative video model based on DiT architecture that creates 768x512 clips at 24 fps, delivering results faster than you can watch them. Instead of long render waits, you iterate through options almost in a dialogue mode, selecting the best take in a few attempts. In BotHub, the model is accessible from Russia without a VPN or foreign card; you can pay with a Russian card in rubles, paying only for actual usage without subscriptions or expiring balances. With over 250 models in one window, you can easily continue a scenario with another neural network. For product tasks, there is a unified OpenAI-compatible API, AES-GCM encryption, and corporate access via contract with invoicing and electronic document management. Marketers can use LTX Video for quick social media clips and creative testing; designers and directors for dynamic storyboards and pre-visualization; product teams for short background animations in interfaces and landing pages; and developers for generating video directly within their services on demand.Frequently asked questions about LTX Video
You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.
ltx-video by Lightricks generates video from text descriptions and animates static images. It is suitable for short clips, scene pre-visualization, animating illustrations, and promotional materials. In BotHub, the model is available from Russia without a VPN or foreign card, with payment in rubles based on actual usage.
The model outputs video: you get a clip generated from a text description or an uploaded image. Exact resolution and duration are not fixed in our data, so refer to the technical parameters in the page header and the results of your first test generations.
There is no specific note about reasoning before answering in our data. The video model has different logic: the quality of the result is determined not by a chain of thought, but by the accuracy of the prompt. Describe the scene, camera movement, lighting, and style in detail — this works better than any hidden reasoning.
Function calling and structured JSON output are not noted in our data — the model's profile is video generation. If you need logic with tools and strict schemas, build a chain via BotHub's unified OpenAI-compatible API: a text model provides parameters, and ltx-video performs the generation.
Images — yes: according to our data, ltx-video accepts an image as input and animates it, so you can set a starting frame, composition, and style as a reference. Audio and video input are not noted in our data, so the main scenario is text and image.
The prompt language is not fixed in our data, so we cannot promise accuracy in Russian — check the result with a short test generation. The BotHub interface and support are in Russian, payment is in rubles, and scene descriptions should be as specific as possible: objects, action, camera, style.