LTX-2.5
Lightricks · Lightricks/LTX-2.5
Weights license: Publisher terms: LTX-2.x Community License Agreement · code and components may use other terms
Quality
No comparable score
Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. Leaderboard (link only)
Reported by the publisher
Runs on
Enough memory 16
A publisher documents a path within this memory, on this platform (CUDA or Apple MPS). Conditional paths need offload or quantization.
Show all 16
One memory tier short 6
The same machines with the next memory size up would have enough.
Hardware profiles grouped by the publisher's documented minimum memory path and platform. Not a measured run.
Consider LTX-2.5 Pro from Lightricks for the text-to-video task (22B parameters).
The catalog lists the publisher's documented memory path under Runs on and has not reviewed other configurations. Actual memory depends on precision, resolution, duration and offload; consult the official source.
Measured speed
No published measurement for this checkpoint
Generation time per clip is shown only when a source publishes it with hardware, build and setup. It is never estimated.
How to run
Publisher-documented memory path: Official minimum for the LTX-2.5 family. Actual memory depends on precision, resolution, duration and offload; consult the official source. Official hardware evidence
Documented ways to run it
Copied as printed in the linked source (read 2026-10-18); not run by this site.
hf download Lightricks/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler \
ltx-2.5-22b-ic-lora-pixel-spatial-upscaler-x2-1.0.safetensors \
--local-dir models/ltx-2.5/lorasuv run python -m ltx_pipelines.dfr_pipeline \
--transformer-path models/ltx-2.5/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors \
--text-encoder-path models/ltx-2.5/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors \
--video-vae-path models/ltx-2.5/vae/ltx-2.5-video-vae-bf16.safetensors \
--audio-vae-path models/ltx-2.5/vae/ltx-2.5-audio-vae-bf16.safetensors \
--detailing-lora models/ltx-2.5/loras/ltx-2.5-22b-ic-lora-pixel-spatial-upscaler-x2-1.0.safetensors \
--spatial-upsampler-path models/ltx-2.5/latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors \
--num-frames 121 \
--seed 42 \
--output-path output_dfr.mp4 \
--prompt "A medium close-up shot features a Caucasian man with a beard, wearing a green and white baseball cap without any letters on the front, and a light blue shirt over a white t-shirt. He is positioned in the center of the frame, looking intently directly at the camera, his eyes focused on camera. His facial expression is one of deep concentration, with his brow slightly raised. As he looks straight at the camera, a quick sniff sound is heard, and then he speaks with a deep male voice and a satisfied tone, saying, 'I think it's so good.' The camera remains static throughout, maintaining a shallow depth of field, which keeps the man in sharp focus while the background is softly blurred, showing a beige wall behind him. After a brief pause, another short, audible sniff is heard. The man then continues to speak, his voice maintaining the same quality, as he states, 'So good. So good.' He elaborates further, emphasizing his point with a final statement, 'This got to be, it's got to be the best tool I've ever seen.'"Evidence level: Publisher documentation linked; no execution reproduced by this site.
Before downloading
- Check the exact checkpoint and license linked here.
- Confirm a compatible runtime and precision or quantization for your platform.
- Allow for context, batch size and any extra media components beyond the weights.
Technical details
What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.
- Checkpoint / version
- Lightricks/LTX-2.5
- Task and modality
- text-to-video · video
- Count and basis
- 22B · manufacturer model card
- Released
- LTX API Changelog, August 11, 2026 · read 2026-10-09source
- Published repository size
- 200.9 GBNot runtime memory or a minimum download.files
- Published components
- 22B diffusion transformer · Gemma4-12B text encoder · Video VAE · Audio VAE
- Runtime and precision
- No local execution verified.
- Commercial use
- Allowed with conditions Companies with USD 10M+ annual revenue need a paid Lightricks license · LTX-2.x Community License (Lightricks/LTX-2.3 LICENSE) · read 2026-10-18license text
Every stored field
- Revision checked
- 5e6e71018ee1756ed329b697a7b4aedc934dfce9
- Library
- diffusion-single-file
- Hub task tag
- image-to-video
- Formats
- safetensors
- Repository created
- 2026-07-23creation is not the model's release
- Repository updated
- 2026-09-01a commit is not a release date
- Hub downloads (30 days) · likes
- 2,107,108 · 9,262this repository only · read 2026-10-25
- Read from the Hub page
- task, task tags, license name, file formatsHub overview and file listing · read 2026-10-18
- Catalog state
- No config or weights found on the Hub
License, parameter count and release date come from the publisher's sources listed on this page (a date no source states is left empty). The hardware requirement has not been reviewed, so memory is a labelled estimate. The repository size, when shown, is the full published download. The leaderboard rows “LTX-2.5 Fast” and “LTX-2.5 Pro” link to this one open checkpoint and share this page; no readable source maps each row to its settings.
Sources
Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.
- Publisher checkpoint and model card
- Weight license and use terms
- Quality benchmark source · Artificial Analysis video · excluded (free tier is internal use only)
- Publisher hardware documentation
Catalog reviewed: 2026-09-22.



















