LTX-2.5 · INT8 ConvRot (h3ddle subset)

A byte-identical mirror of the four files H3ddle loads from Lightricks/LTX-2.5, revision 6c7e5e5.

Nothing here was retrained, merged, pruned, quantized, or repackaged. The INT8 ConvRot quantization is Lightricks' own, published in that repository; these are the same bytes under the same paths. Every file's SHA-256 matches upstream, and you can check that against the checksums below.

Why this mirror exists

The upstream repository is gated, so an application cannot fetch it on a user's behalf without that user first accepting terms on the website. This copy carries the same Agreement — see LICENSE, which is a complete copy — so the terms travel with the weights rather than being skipped.

Using these weights binds you to the LTX-2.x Community License Agreement, including the use-based restrictions in Section 4 and Attachment A in their entirety. Read them. They restrict what you may generate, and Section 6 separately forbids circumventing watermarking, provenance or latent-disclosure mechanisms. A commercial entity as defined in Section 2 needs a paid licence from Lightricks.

What is here, and what is not

file bytes
diffusion_models/ltx-2.5-22b-distilled-transformer-comfy-int8-convrot.safetensors 21,504,034,224
text_encoders/gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors 15,372,969,374
vae/ltx-2.5-video-vae-conv-bf16.safetensors 1,452,269,922
vae/ltx-2.5-audio-vae-bf16.safetensors 364,866,540

38.69 GB in total, against upstream's ~180 GB. Deliberately absent: the BF16 and NVFP4 transformers, the dev (non-distilled) transformer, the LoRA, the latent upscalers, the duration head, and the non-conv video VAE. The app runs the distilled checkpoint at eight steps and does not use the stage-2 upscale ladder, so those files would be download with nothing behind it.

For anything other than that subset, go upstream — this is not a replacement for the model card, the paper, or the full release.

Credit

LTX-2.5 is by Lightricks. All copyright, patent, trademark and attribution notices in the original release are retained here; the model, the quantization and the licence are theirs, and the only thing this repository adds is a different URL.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for PulpCut/LTX-2.5-INT8-ConvRot-safetensors

Finetuned
(13)
this model