Skip to main content
ToolPotion
AI Advisor
Submit a Tool (Free)

LTX-2.5 — Hugging Face

Featured
AI ModelsAI Models & LLMsOpen source · Web

LTX-2.5 is an open world model designed for generating synchronized, high-fidelity video and audio from various inputs. It offers full control and customization for local execution, making it suitable for commercial and production use under the LTX-2.x Community License.

View Model
Share
View Model
Share

LTX-2.5 is a cutting-edge open world model developed by Lightricks, designed to generate synchronized, high-fidelity video and audio from text, image, and video inputs. This model is built for local execution and fine-tuning, providing users with full control and customization options. It is particularly beneficial for those in emerging domains such as robotics and physical AI, where the need for high-quality multimedia generation is paramount.

Read More

One of the standout features of LTX-2.5 is its native multishot generation capability, allowing users to create connected scenes in a single pass. This means that multiple shots can maintain character identity, environment, lighting, voice, and visual style across cuts, enhancing the storytelling experience. Additionally, the model employs diffusion fidelity rendering, dynamically allocating compute resources based on scene complexity, ensuring that detail is rendered where it matters most while remaining efficient elsewhere.

The introduction of a new diffusion video decoder replaces the VAE reconstruction stage, resulting in sharper faces, improved textures, and better motion with fewer artifacts in demanding scenes. The custom Gemma 4 12B text encoder is another significant advancement, capable of holding complex prompts together without losing details across longer sequences. Furthermore, a prompt enhancer expands short prompts into richer cinematic instructions, enhancing the overall output quality.

For those looking to predict clip lengths, LTX-2.5 includes an optional duration predictor that sets the frame count based on the prompt, streamlining the workflow. The model also features a substantially improved distilled version, which retains much of the full model's visual quality and motion consistency while being smaller and faster.

LTX-2.5 is available under the LTX-2.x Community License, allowing for commercial and production use at no cost, although the transfer of fine-tunes may require a paid license. Users can access the model through various integration options, including Python and ComfyUI, making it versatile for different technical environments. With its robust capabilities and open-source nature, LTX-2.5 is poised to advance and democratize artificial intelligence in multimedia generation.

  • CategoryAI Models & LLMs
  • Pricing ModelOpen source
  • DeploymentSelf-hosted
  • PlatformsWeb

  • Open World Model

  • High-Fidelity Video Generation

  • High-Fidelity Audio Generation

  • Native Multishot Generation

  • Diffusion Fidelity Rendering

  • Custom Gemma 4 12B Text Encoder

  • Prompt Enhancer

  • Duration Predictor

  • Distilled Model Available

  • Commercial Use License

  1. Access page: Visit the LTX-2.5 model page on Hugging Face.

  2. Load model: Download the necessary weights and components for LTX-2.5.

  3. Configure environment: Ensure your setup meets the requirements (Python >= 3.12, CUDA >= 12.7, PyTorch ~= 2.7).

  4. Integrate: Use the provided CLI flags to load the model components in your application.

  5. Fine-tune: Utilize the LTX-2 Trainer to fine-tune the model as needed.

  • Video Production
  • Audio Creation
  • Robotics Simulation
  • Game Development
  • Educational Content

From Lightricks

A model in LTX-2.5 Pro.

LTX-2.5 Reviews

Loading...

Popular AI Tools Like LTX-2.5

LTX-2

AI Models

LTX-2 is a DiT-based audio-video foundation model designed to generate synchronized video and audio. It combines modern video generation techniques with open weights, enabling…

AI Models & LLMs
View Tool

AI Models

DiT-based audio-video foundation model designed to generate synchronized video and audio. It combines modern video generation techniques with open weights, enabling…LTX-2 is a DiT-based audio-video foundation model designed to generate synchronized video and audio. It combines modern video generation techniques with open weights, enabling…

FeaturedAI Models & LLMs
See the Top 5 AI Models

LTX-2.5 Pro

AI Models

LTX-2.5 Pro is an advanced open-weight diffusion transformer model designed for multimodal video, audio, and world simulation. It offers high-fidelity rendering, smoother motion,…

AI Models & LLMsMedia & Entertainment
View Tool

AI Models

Advanced open-weight diffusion transformer model designed for multimodal video, audio, and world simulation. It offers high-fidelity rendering, smoother motion,…LTX-2.5 Pro is an advanced open-weight diffusion transformer model designed for multimodal video, audio, and world simulation. It offers high-fidelity rendering, smoother motion,…

AI Models & LLMsMedia & Entertainment
See the Top 5 AI Models

Ray3.2 is a versatile AI video model that transforms creative intent into scalable video workflows. It offers enhanced control, continuity, and cinematic direction across multiple…

AI Models & LLMs
View Tool

Ray3.2 is a versatile AI video model that transforms creative intent into scalable video workflows. It offers enhanced control, continuity, and cinematic direction across multiple…

FeaturedAI Models & LLMs
See the Top 5 AI Models

LTX-Video is a DiT-based video generation model by Lightricks, capable of producing high-quality, real-time videos. It generates 30 FPS videos at 1216×704 resolution, trained on a…

AI Models & LLMs
View Tool

DiT-based video generation model by Lightricks, capable of producing high-quality, real-time videos. It generates 30 FPS videos at 1216×704 resolution, trained on a…LTX-Video is a DiT-based video generation model by Lightricks, capable of producing high-quality, real-time videos. It generates 30 FPS videos at 1216×704 resolution, trained on a…

AI Models & LLMs
See the Top 5 AI Models

Wan2.1-T2V-14B is a state-of-the-art video generative model that excels in text-to-video, image-to-video, and video editing tasks. It supports consumer-grade GPUs and generates…

AI Models & LLMs
View Tool

State-of-the-art video generative model that excels in text-to-video, image-to-video, and video editing tasks. It supports consumer-grade GPUs and generates…Wan2.1-T2V-14B is a state-of-the-art video generative model that excels in text-to-video, image-to-video, and video editing tasks. It supports consumer-grade GPUs and generates…

AI Models & LLMs
See the Top 5 AI Models

Wan 2.6

AI Apps

An AI video generator on the JXP platform that creates 1080p videos from text, images, or reference videos with multi-shot storytelling, reference-based character and voice…

AI Video GeneratorsMedia & Entertainment
View Tool

AI Apps

An AI video generator on the JXP platform that creates 1080p videos from text, images, or reference videos with multi-shot storytelling, reference-based character and voice…

AI Video GeneratorsMedia & Entertainment
See the Top 250 AI Apps

SpecialX

AI Apps

SpecialX is an agentic AI platform for creating, posting and monetizing content. It generates images and video with more than 15 AI models, auto-posts to social platforms on a…

AI Video Generators
View Tool

AI Apps

Agentic AI platform for creating, posting and monetizing content. It generates images and video with more than 15 AI models, auto-posts to social platforms on a…SpecialX is an agentic AI platform for creating, posting and monetizing content. It generates images and video with more than 15 AI models, auto-posts to social platforms on a…

AI Video Generators
See the Top 250 AI Apps

Flux 3 by Black Forest Labs is a multimodal foundation model that learns from images, videos, and audio. It enables creators to generate content seamlessly across different media…

AI Models & LLMs
View Tool

Flux 3 by Black Forest Labs is a multimodal foundation model that learns from images, videos, and audio. It enables creators to generate content seamlessly across different media…

AI Models & LLMs
See the Top 250 AI Apps
1 of 8