LTX Video 0.9.7 Distilled
Neural Network
LTX Video 0.9.7 Distilled is an accelerated Lightricks video model available in BotHub for text-to-video generation.
Specifications
- Input
- text, images
- Output
- video
- Resolution
- 480, 720
- Aspect ratio
- 16:9, 1:1, 9:16
- Frame rate, fps
- 24, 25, 48, 50
Video generation
(duration 8 sec., 720p)
Video generation
(duration 8 sec., 1080p)
How it works LTX Video 0.9.7 Distilled?
LTX Video 0.9.7 Distilled is a distilled Lightricks video model: it generates faster than LTX-Video 13b with only a slight drop in quality, making it ideal for iterating through many options quickly. In BotHub, it is accessible from Russia without a VPN or foreign card; payment is made in rubles via Russian cards on a pay-as-you-go basis, with no subscription required. Over 250 models are available in one window for easy switching. For production tasks, there is a unified OpenAI-compatible API and corporate terms: contracts, invoices, electronic document management, and an admin panel with limits. Use this model to create rough clips and storyboards from text descriptions, prepare short dynamic inserts for social media and advertising, test ideas before final rendering in a heavier model, and bring concepts to life for presentations and pitches.Frequently asked questions about LTX Video 0.9.7 Distilled
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.
This is a Lightricks video model: it creates short clips from text descriptions and animates uploaded images. It is suitable for dynamic intros, advertising and social media formats, animating illustrations and product shots, as well as quick scene drafts before expensive production.
You get a finished video clip that can be downloaded or passed on via API. See the technical header of the page and request settings for exact duration and resolution parameters. The Distilled version is focused on fast generation of short clips.
A separate reasoning mode is not indicated in our data, and the model's task is different: it does not write text, but assembles frames. Think through the scene logic in the prompt or connect a BotHub text model — switching between models happens in one window.
Function calling and structured JSON output are not indicated for this model in our data: this is a video generator, not a text assistant. You can access it via the unified BotHub OpenAI-compatible API, so integrating generation into your service is easy.
Images — yes: the image-to-video mode animates the uploaded frame, preserving the composition and style of the reference. Input of audio or finished video is not indicated in our data. The most predictable scenario is an image plus a short description of the desired movement and camera.
Prompts should be as specific as possible: who is in the frame, what they are doing, how the camera moves, what the lighting and mood are. The BotHub interface is in Russian, payment is accepted via Russian cards in rubles, and access from the Russian Federation works without a VPN or foreign card.