LTX Video 2.5 Pro
LTX Video 2.5 Pro is a production-grade, open-weights video model that generates high-fidelity 1080p and 4K clips up to 10 seconds with synchronized audio, available via API or self-hosted.
Overview
What is LTX Video 2.5 Pro
LTX Video 2.5 Pro is a high-performance AI video model from LTX (spun out of Lightricks) that generates up to 10-second clips in 1080p or 4K from text or image prompts. It supports synchronized audio, precise motion control, and is fully open weights — deployable via API, on-prem, or locally.
Running it privately on Venice
On Venice, LTX Video 2.5 Pro runs under an anonymized privacy tier — your image and text prompts are not stored, profiled, or used for training. You retain full sovereignty over creative inputs while accessing the model’s full capabilities, including audio and high-resolution output, without vendor lock-in. The open weights allow permissionless use across workflows.
Assessment
Strengths and limitations
- Fully open weights: you can self-host, fine-tune, or integrate into private pipelines without restrictions.
- Generates native 4K HDR video with synchronized audio, ideal for professional production workflows.
- Supports both text-to-video and image-to-video modes with clean, artifact-free motion.
- Fast generation: a 10-second clip can be produced in under 7 seconds on high-end hardware.
- Precise prompt control and multishot continuity for character and scene consistency.
- Closed to uncensored use: the model applies content moderation filters and is not designed for unrestricted generation.
- Limited to clips of 10 seconds or shorter, which may not suit long-form storytelling.
- No end-to-end encryption or TEE support on Venice, limiting privacy to anonymization only.
Samples
Sample outputs
Generated on Venice with our standard prompt suite — the same prompts we run through every model of this type, so you can judge it like-for-like.
Slow aerial drone shot gliding over a misty mountain valley at golden hour, sunlight piercing clouds onto a winding river, ancient pine forests on either side, ultra-smooth motion, professional color grading, atmospheric haze, 4K
Calm ocean waves rolling onto a black-sand beach at sunrise, golden light on wet sand, foam dissolving into the shore, a single silhouetted figure at the waterline, smooth continuous forward push, serene cinematic atmosphere
A slow tracking shot through a rain-soaked Tokyo street at night, neon reflecting in puddles, steam rising from a food cart, a person with a translucent umbrella, shallow depth of field, teal-and-orange grade, smooth steady camera
Capabilities
What it supports
- Text to video
- Image to video
- Reference to video
- Native audio generation
Variants
LTX Video 2.5 Pro model variants
LTX Video 2.5 Pro runs on Venice as 2 variants of the same underlying model. Pick by what you're starting from: a written prompt, a still image, reference images, or an existing clip. Each variant is its own model id on the API; the generation quality is the same across the family.
| Variant | What it is | Clip lengths | Resolutions | Aspect ratios | Audio | Model ID |
|---|---|---|---|---|---|---|
| Text to Video | Generate a clip from a written prompt | 6s, 8s, 10s | 720p, 1080p | 16:9, 9:16 | ltx-2-5-pro-text-to-video | |
| Image to Videoflagship | Animate a still image into motion | 6s, 8s, 10s | 720p, 1080p | auto, 16:9, 9:16 | ltx-2-5-pro-image-to-video |
Capability data comes straight from the Venice model API and refreshes with every catalog ingest. The specs and pricing on this page are captured from the flagship variant; pass the model id of the variant you want to the API.
LTX Video 2.5 Pro Text to Video
Generate a clip from a written prompt. Supports clips of 6s, 8s, 10s, 720p, 1080p output, 16:9, 9:16 aspect ratios, with native audio.
ltx-2-5-pro-text-to-videoLTX Video 2.5 Pro Image to Video
Animate a still image into motion. Supports clips of 6s, 8s, 10s, 720p, 1080p output, auto, 16:9, 9:16 aspect ratios, with native audio.
ltx-2-5-pro-image-to-videoSpecifications
Datasheet
- Maker
- LTX (Lightricks)
- Released
- May 2026
- Modality
- Text-to-video, image-to-video, audio
- Max resolution
- 4K HDR
- Resolutions
- 720p, 1080p
- Clip lengths
- 6s, 8s, 10s
- Mode
- image-to-video
- Aspect ratios
- auto, 16:9, 9:16
- Audio
- Yes
- Privacy on Venice
- Anonymized — prompts not stored
- Available on Venice since
- Aug 2026
- License
- Open Weights
API
Call it from your code
Venice exposes this model through the REST API. Queue a generation with the model id.
curl https://api.venice.ai/api/v1/video/queue \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "ltx-2-5-pro-image-to-video",
"prompt": "Aerial drone shot over a misty mountain valley at golden hour"
}'
# Use the returned queue_id with https://api.venice.ai/api/v1/video/retrieve.
# Call /video/complete after downloading if needed.Pricing
What it costs on Venice
Pay per clip on Venice — price scales with resolution and duration (6s–10s), from $0.79.
New Venice accounts include a free daily allowance and 500 welcome credits — no credit card required.
Alternatives
How it compares
| Model | Max resolution | Strongest at | Open weights | Price (Venice) |
|---|---|---|---|---|
| LTX Video 2.5 Pro | 4K HDR | Production-grade open video | Yes | from $0.79 |
| Wan 2.7 | 1080p | Stylized short clips | Yes | from $0.55 |
| Kling O3 Pro | 4K | Action and camera motion | No | from $0.46 |
| Vidu Q3 | 1080p | Longer clips (up to 16s) | No | from $0.27 |
The only open, high-fidelity video model on Venice with audio and 4K support.
Use cases
What it is good for
- 01Creating short-form social media videos from still images or text descriptions.
- 02Generating cinematic clips with consistent characters and camera motion for storyboarding.
- 03Producing professional-grade 4K HDR content for marketing or media teams.
- 04Integrating into custom video pipelines via ComfyUI or API with full control over output.
- 05Running locally for privacy-sensitive or enterprise video generation workflows.
Prompting
Getting better results
Use clear, descriptive prompts with explicit timing cues (e.g., 'pan left over 3 seconds') for better motion control.
For image-to-video, ensure the input image is high resolution and well-lit for optimal motion rendering.
Specify aspect ratio (16:9, 9:16) and duration (6s, 8s, 10s) in the prompt to match platform needs.
Leverage native audio support by describing sound effects or music style in the prompt.
Version history
Predecessor with open weights and 4K support.
Current — improved fidelity, motion, and audio sync.
FAQ
Frequently asked questions
LTX Video 2.5 Pro is an open-weights AI video model developed by LTX (from Lightricks) that generates high-fidelity, up to 10-second video clips in 1080p or 4K from text or image prompts, with synchronized audio and support for precise motion control.
On Venice, pricing starts at $0.79 per clip for 720p at 6 seconds, scaling with resolution and duration. You pay per clip — no subscription required.
Yes, it is fully open weights — model weights are publicly available. You can run it locally or via API. However, commercial use may require a license depending on scale.
Yes, LTX Video 2.5 Pro generates synchronized audio with video, making it suitable for content that requires sound effects, voice, or music.
Yes. Venice runs LTX Video 2.5 Pro under an anonymized privacy tier — your prompts are not stored, profiled, or used for training, ensuring private, permissionless access.
It supports 720p, 1080p, and native 4K HDR output, with aspect ratios including auto, 16:9, and 9:16.
No — LTX Video 2.5 Pro is a generative video model and does not support external tool use or function calling. It focuses on video and audio synthesis from prompts.
Yes. The variant 'ltx-2-5-pro-image-to-video' is specifically designed to animate still images into 6s–10s video clips with motion and audio.
LTX Video 2.5 Pro offers higher resolution (up to 4K vs 1080p), native audio, and more precise motion control. Wan 2.7 is open weights and fast but better suited for stylized short clips without audio.
Run LTX Video 2.5 Pro privately
No prompt logging. No data used for training.