The Open Weights
LatestModelsLeaderboardsCompanies
Subscribe
The Open Weights

The daily record of open-source AI. New model releases, leaderboards, and what's coming next — written for people who ship.

Refreshed every 12 hours

Discover

  • Latest releases
  • New today
  • Trending models

Browse

  • All models
  • Companies
  • Categories
  • Leaderboards

About

  • About
  • Editorial policy
  • Hardware estimates
  • RSS feed
  • llms.txt
  • Newsletter

© 2026 The Open Weights. An independent publication.

PrivacyTermsSMSAggregated by Claude · curated by humans.
LatestLightricks2.5
LightricksImage → Video

Lightricks Releases LTX-2.5 Video Model

The latest LTX generator handles text-to-video, image-to-video, and audio-video pipelines in one open release.

Jul 23, 2026
NotableOther
LTX-2.5

Lightricks has published LTX-2.5, the newest version of its LTX video generation family, on Hugging Face. The model handles both text-to-video and image-to-video generation, and the release notes an audio-video pipeline alongside the core visual synthesis capabilities.

LTX has been one of the more visible efforts to bring capable video generation into openly available weights, an area still dominated by closed, API-only systems. By packaging multiple input modalities into a single release, Lightricks is positioning LTX-2.5 as a general-purpose creative tool rather than a narrow research artifact.

Why it matters

Video generation remains one of the most compute-hungry and least open corners of the current AI landscape. Models that ship with weights let developers, studios, and researchers experiment locally, fine-tune for specific styles, and build products without depending on a single vendor's endpoint.

A few things worth noting about this release:

  • It covers text-to-video and image-to-video in one model, easing the jump between prompt-driven and reference-driven workflows.
  • It references an audio-video pipeline, hinting at synchronized sound-and-motion generation.
  • It ships under a custom license, so teams should review the terms on the model page before commercial use.

As with any video model, the practical test will be output quality, speed, and how well the weights hold up against closed competitors once the community starts running them. For now, LTX-2.5 adds another credible option to the short list of open video generators.

Sources

  • Lightricks/LTX-2.5

    Hugging Face

    Visit
OlderUpstage's Solar Open2 arrives as a 250B MoE modelUpstage · Text / LLM · 4 months agoNewerKwaipilot Releases KAT-Coder V2.5 Dev, an Agentic MoE CoderKwaipilot · Code · 4 months ago

Get the model

Hugging Face

Specs

LicenseOTHER
Downloads8.2K
Likes168

Modalities

Text → VideoImage → Video
4 versions — view changelog

The Weekly Weights

Every open release that mattered, one email a week.

0 comments

No comments yet. Be the first to weigh in.

More from Lightricks

All Lightricks releases →
LTX-2.5
Lightricks/Image → Video

Lightricks Releases LoRA for AI Lip-Dubbing

The new 'Identity-Control' adapter fine-tunes the company's LTX-2.3 video model to create realistic lip-syncing for dubbing workflows.

May 11, 2026
LTX-2.5
Lightricks/Image → Video

Lightricks LTX-2.3 Generates Video and Audio Together

The new model, based on Stable Video Diffusion, can create video and a corresponding soundtrack simultaneously from text, image, or audio prompts.

Mar 4, 2026
LTX-2.5
Lightricks/Image → VideoConsumer GPU

Lightricks Releases LTX-2 Multimodal Video Generator

The new diffusion model from the creative app company can generate short video clips from text, images, audio, and even other videos.

Jan 3, 2026

More in Image → Video

All Image → Video →
LongCat-Video-Avatar-1.6
Meituan/Image → Video

Meituan's LongCat Adds Audio-Driven Avatar Video

The LongCat team releases an image-to-video model that animates still portraits from audio input.

Nov 13, 2026
NVIDIA/Image → Video

NVIDIA Releases Cosmos 3 for World Simulation

The new open models push NVIDIA's world-foundation effort toward interactive, real-time video generation.

Nov 5, 2026
NVIDIA/Text → Video

NVIDIA's Cosmos 3 Brings Open Interactive World Models

The new open release pushes beyond passive video generation toward simulated worlds that respond to input.

Nov 5, 2026