Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · Lightricks

LTX-Video-0.9.5

LTX-Video-0.9.5 is a 1.92B-parameter video-generation model from Lightricks. According to the model card, it supports text-to-video and image-to-video generation.

Publisher
Lightricks
Task
text-to-video
Model type
Unknown
License
other
Library
diffusers
Publication status
Accepted · not indexed

Model overview

LTX-Video-0.9.5 is published by Lightricks as a text-to-video model. Safetensors metadata reports 1,923,385,472 parameters. According to the model card, it is a DiT-based model for high-quality video generation supporting text-to-video and image-plus-text-to-video.

Recorded capabilities

DiT video generation at 30 FPS

According to the model card, the publisher describes DiT-based generation at 30 FPS and 1216x704 resolution.

Text-to-video and image-to-video

According to the model card, the model supports both text-to-video and image-plus-text-to-video generation.

1.92B model with Diffusers

Safetensors metadata reports 1,923,385,472 parameters, and hub metadata lists diffusers with LTXPipeline support.

Resolution and prompting guidance

According to the model card, resolutions should be divisible by 32 with frame counts of 8 plus 1, and prompts should be elaborate English.

Use cases in the source record

  • Text-to-video generation from elaborate English prompts using the documented inference and Diffusers workflows.
  • Image-plus-text-to-video generation using the documented image-to-video pipeline path.

Limitations and unknowns

  • No evaluation results were extracted from this record.
  • Provider state is historical snapshot data, not independently refreshed current availability.
  • Capability and performance information comes from the publisher model card and has not been independently verified by Ethen.

Source and provenance

Source: Lightricks/LTX-Video-0.9.5

Captured: Unknown. Processed: 2026-09-07T19:34:33.477415+00:00.

LTX-Video 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 hair and light s…

F001F002F003F004F005F006F007F008F009F010F011F016F017F019