Lightricks Open-Sources LTX-2.5 Video Model with Native Multishot
Lightricks officially released and open-sourced the video generation model LTX-2.5 on August 11-12. The model features a comprehensive overhaul of the generation pipeline, trained with larger datasets and reinforcement learning post-training. It supports native multishot generation, synchronized audio-video generation (48 kHz), and high-fidelity rendering, with extremely fast inference (e.g., generating a 10-second 4K video from a single image in 6.8 seconds). The model offers 22B distilled and full-precision weights, natively compatible with ComfyUI and Diffusers, and includes 9 preset ComfyUI workflows. It topped Hugging Face trending charts and is available on fal and Runware. Current conclusion: LTX 2.5 provides a powerful open-source tool for video creation, but facial detail issues persist, raising competitiveness concerns.
Confirmed
- The model offers 22B distilled and full-precision weights, using a new diffusion decoder and compression model to reduce compression artifacts while maintaining fast inference.
- Native multishot generation processes multiple shots as a continuous sequence, outputting coherent shots in a single generation, maintaining character, environment, and audio consistency.
- The generation pipeline was overhauled to reduce prompt retries and texture artifacts, using a customized Gemma 4 12B as the backbone for prompt understanding.
- Introduces Diffusion Fidelity Rendering, allocating more compute to complex scenes for improved quality.
- Supports text-to-video, image-to-video, and synchronized audio-video generation, natively compatible with ComfyUI and Diffusers, with 9 preset ComfyUI workflows.
- Excellent backward compatibility: developers can directly replace weights without upgrading ComfyUI or changing workflows; most LTX 2.3 LoRAs work with 2.5.
- Topped Hugging Face trending and is available on fal and Runware.
Unconfirmed
- According to @EverythingMacPro's observation of sample videos, the facial distortion weakness of the LTX series seems not fully fixed. He expressed concerns about LTX 2.5's market competitiveness given competitors like MiniMax H3 have raised the bar.
Why it matters
- The open-source nature and multi-platform support of LTX 2.5 significantly lower the barrier for developers to use advanced video generation technology. Its native multishot generation and high-fidelity rendering provide new open-source solutions for film production and complex scene handling.
2026-08-11 ~ 2026-08-13 · 24 related posts
- Episode 1: LTX 2.5 vs MiniMax H3: Speed Dominates but Quality Debated(2026-08-11, 23 posts)
- Episode 2: Lightricks Open-Sources LTX-2.5 Video Model with Native Multishot(2026-08-11, 24 posts)
- Episode 3: LTX 2.5 hands-on: blazing speed and 6GB local runs, but action and scripted dialogue fall short(2026-08-13, 11 posts)
Primary sources
- LTX 2.5 Video Model Released — just_shady · 2026-08-11
- LTX 2.5 Video Model Released, Face Distortion Issues Persist — EverythingMacPro · 2026-08-11
- Lightricks Announces Open Weights for LTX Video 2.5 Today — SanDiegoDude · 2026-08-12
- Lightricks Releases LTX-2.5 Video Generation Model — PixelatedCaffeine · 2026-08-12
- Open-Source Video Generation Model LTX-2.5 Released — TechnologyTailors · 2026-08-12
- LTX 2.5 Open Video Model Released: Native Multi-Shot Generation — linoy_tsaban · 2026-08-12
- LTX-2.5 Video Model Launches: Native Audio Generation and Up to 4K Resolution — aziz4ai · 2026-08-12
- LTX-2.5 Video Model Released: Features Multishot Scenes and High Fidelity — linoy_tsaban · 2026-08-12
- [source] LTX-2.5 Released: Native Multishot Video Generation in One Pass — ltx_model · 2026-08-12
- LTX 2.5 Video Generation Model Goes Live on fal with Fidelity Rendering — OdinLovis · 2026-08-12
- LTX-2.5 Multimodal Video Generation Model Released on Hugging Face — cocktailpeanut · 2026-08-12
- LTX 2.5 Video Model Confirmed to Support Most LTX 2.3 LoRAs — ArttTaku · 2026-08-12
- LTX-2.5 Open-Source Video Model Rebuilt to Cut Retries and Artifacts — aigleeson · 2026-08-12
- LTX-2.5 Open-Sources Native Multishot Video Generation for Character Consistency — JafarNajafov · 2026-08-12
- LTX-2.5 Video Model Dropping with Open Weights: Better Multi-Shot & Prompt Adherence — cocktailpeanut · 2026-08-12
- LTX-2.5 Tops Hugging Face Trending with Multi-Modal Video Generation — Lightricks · 2026-08-12
- LTX-Video 2.5 Tested: Drop-in Weight Replacement Works Flawlessly with Old Workflows — Austin9981 · 2026-08-12
- LTX 2.5 Released: Native Multishot, 9 ComfyUI Workflows, Backward Compatible — RobbaW · 2026-08-12
- LTX-2.5 Video Model Hits Diffusers with Native Audio Generation — RisingSayak · 2026-08-12
- [source] Open-Source World Model LTX-2.5 Released: Generates 10s 4K Video in 6.8s — dr_cintas · 2026-08-13
- Lightricks Open-Sources LTX-2.5: Generates 10s Video in 6.8s — xiaohu · 2026-08-13
3 near-duplicate retellings: linoy_tsaban · JafarNajafov · dr_cintas