Distilled speed tradeoff
According to the model card, this distilled release is faster with less VRAM use and slight quality reduction, suited to rapid iterations.
Open Source Model Profile · Lightricks
LTX-Video-0.9.8-13B-distilled
LTX-Video-0.9.8-13B-distilled is a 13.04B-parameter image-to-video model from Lightricks. According to the model card, the distilled variant favors faster generation with less VRAM use and slight quality reduction.
- Publisher
- Lightricks
- Task
- image-to-video
- Model type
- Unknown
- License
- other
- Library
- diffusers
- Publication status
- Accepted · not indexed
Model overview
LTX-Video-0.9.8-13B-distilled is published by Lightricks as an image-to-video model. Safetensors metadata reports 13,042,569,344 parameters with diffusers library support. According to the model card, it belongs to the LTX-Video family described as DiT-based video generation.
Recorded capabilities
13.04B Diffusers record
Safetensors metadata reports 13,042,569,344 parameters with diffusers library and LTXConditionPipeline tagging.
Diffusers compatibility
According to the model card, LTX Video is compatible with the Diffusers Python library for image-to-video generation.
Prompt and shape guidance
According to the model card, prompts should be in English with elaborate detail, and resolutions and frame counts follow divisibility rules.
Use cases in the source record
- Image-to-video generation using the publisher-documented inference script or Diffusers workflows.
- Rapid video iteration where the publisher-described distilled speed and lower-memory tradeoff is acceptable.
- Multi-condition video tests using the publisher-documented image and short-segment conditioning options.
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 architecture or model-type values were 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-0.9.8-13B-distilled
Captured: Unknown. Processed: 2026-09-07T19:35:41.450031+00:00.
LTX-Video 0.9.8 13B 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. Image-to-video examples Models & Workflows Name Notes inference.py config ComfyUI workflow (Recommended) ltxv-13b-0.9.8-dev Highest quality, requires more VRAM ltxv-13b-0.9.…
F001F002F003F004F005F006F007F008F010F011F014F015F017F018F020