INT8/INT4 ConvRot Quantizations of LTX-2.5 Currently, high-movement scenes suffer a lot from smearing ltx-2-community-license-agreement <a target="_blank" rel="ugc" href="https://github.com/Lightricks/LTX-2/blob/main/LICENSE.md">https://github.com/Lightricks/LTX-2/blob/main/LICENSE.md</a>

LTX 2.5 INT8/INT4 ConvRot

ltx-2.5-22b-distilled-transformer-comfy-int8-convrot.safetensors

LTX 2.5 DISTILLED INT8

LTX 2.5 DISTILL INT4 W4A8

LTX 2.5 DEV INT4 W4A8

LTX 2.5 DEV INT8

LTX-2.5 is an open world model with open weights, built for local execution and fine-tuning. Its established use is generating synchronized, high-fidelity video and audio from text, image, and video inputs; applicability to emerging domains such as robotics and physical AI is developing.Full control and customization — self-host on your own infrastructure. No per-generation billing, no per-seat lock-in, no forced API dependency. Revenue is measured across the whole entity, including subsidiaries and affiliates under common control. The full, binding terms live in <code>LICENSE</code>.<h2 id="what's-new-in-ltx-2.5">What's new in LTX-2.5</h2><ul><li>Native multishot generation — generate connected scenes in a single pass: multiple shots that hold character identity, environment, lighting, voice, and visual style across cuts (previous versions produced a single continuous shot).</li><li>Diffusion fidelity rendering — Instead of locking every scene to one compression rate, our model dynamically allocates compute by scene complexity and budget, rendering flawless detail where it matters, efficient everywhere else.</li><li>New diffusion video decoder — replaces the VAE reconstruction stage; sharper faces, textures, and on-screen text, better motion, and fewer artifacts in demanding scenes.</li><li>Custom Gemma 4 12B text encoder — holds complex prompts together (multiple characters, camera moves, lighting, actions) instead of dropping details across a longer sequence.</li><li>Prompt enhancer — expands a short prompt into richer cinematic instructions at minimal extra compute.</li><li>Duration predictor (optional) — an opt-in node predicts a clip's length from the prompt and sets the frame count for you, instead of relying on a fixed-duration parameter.</li><li>Substantially improved distilled model — retains much more of the full model's visual quality, prompt adherence, and motion consistency in a smaller, faster checkpoint.</li></ul>

Files with SHA256: c4279eeff115cbeaca494bd2183e7d768c38fe85a184dc6afbb7159157c44334