LTX-Video-0.9.7-distilled

Model overview

LTX-Video-0.9.7-distilled is published by Lightricks as a text-to-video model. Safetensors metadata reports 13,042,569,344 parameters, and tags identify the diffusers library with Lightricks/LTX-Video base-model lineage. According to the model card, the distilled variant trades a slight quality reduction for faster generation and lower VRAM use.

Recorded capabilities

Use cases in the source record

• Text-to-video generation using the publisher-documented inference script or Diffusers LTXConditionPipeline workflows.
• Image-plus-text-to-video experiments following the publisher's conditioning and prompt guidance.
• Rapid video iteration where the publisher-described distilled speed and lower-memory tradeoff is acceptable.

Limitations and unknowns

• The recorded license value is other without further extracted terms; full license text was not extracted.
• No evaluation results were extracted from this record.
• No context-window value was extracted from this record.
• Publisher speed, quality, and real-time claims come from the model card and were not independently measured.
• Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: Lightricks/LTX-Video-0.9.7-distilled

Captured: Unknown. Processed: 2026-09-07T19:35:12.895085+00:00.

LTX-Video 0.9.7 Distilled Model Card This model card focuses on the model associated with the LTX-Video model, codebase available here . LTX-Video is the first DiT-based video generation model capable of generating high-quality videos in real-time. It produces 30 FPS videos at a 1216×704 resolution faster than they can be watched. Trained on a large-scale dataset of diverse videos, the model generates high-resolution videos with realistic and varied content. We provide a model for both text-to-video as well as image+text-to-video usecases A woman with long brown hair and light skin smiles at another woman... A woman with long brown…