LTX-2.5 Pro · Text to Video

ABOUT THE WORKFLOW

Generate a Video from Text
Describe a scene and get a video clip back. LTX-2.5 Pro is the quality-optimized tier of the LTX-2.5 family, generating up to 1080p at 25 fps with sharp faces, readable on-screen text, and strong motion in complex scenes. A sample fashion prompt is pre-filled.

Partner node. This workflow calls an external API, so each run uses credits from your API wallet. No API key needed. Floyo handles the connection.

Model

• LTX-2.5 Pro by LTX (Lightricks). A 22B-parameter open-weights video model released August 2026. Pro is the quality tier, strong at sharp faces, readable text in video, and complex scenes with crowds or fast motion. Supports native multishot and camera motion presets.

HOW IT WORKS

Step 1. Write your prompt
Describe the scene you want. Subject, action, camera move, lighting, mood. A sample fashion prompt is pre-filled. Replace it with your own.
Works great with: cinematic scenes · fashion · product · motion design

Step 2. Pick duration and ratio
Set clip length in seconds and choose an aspect ratio. 16:9 is the default. Longer clips cost more.

Step 3. Set camera motion (optional)
Choose a camera movement preset from the dropdown, or leave it on none and describe the camera in your prompt instead.

Step 4. Hit run and download
The model generates the clip and returns it as a video file. Preview it in the workflow, then download.
Ready for: Premiere · DaVinci Resolve · After Effects · any NLE

First time? Leave every setting as-is. The defaults (6 seconds · 1080p · 16:9 · 25 fps · no camera motion) are the right starting point for almost everyone.

RECOMMENDED SETTINGS

Quick-start guide. Find the goal that matches yours and copy the settings.

• Standard generation (most people) — 6 seconds · 1080p · 16:9 · 25 fps · no camera motion. The right starting point for almost everyone.

• Want a vertical video — Switch aspect ratio to 9:16 for stories, reels, or portrait content.

• Want a specific camera move — Pick a preset from the camera motion dropdown, or describe the move in your prompt. "Slow dolly forward" in the prompt works if the preset does not match what you need.

• Want a longer clip — Increase duration. Each additional second costs more per run. Pro maxes out at shorter clips than the Fast tier.

• Need 4K or clips up to 20 seconds — Switch to the LTX-2.5 Fast workflow. Pro caps at 1080p.

• The video does not match the prompt — Rewrite the prompt before changing settings. Specific scene direction matters more than resolution. Name the subject, the action, the camera, and the lighting.

Prompt: Write it like a shot brief. "A stylish young adult walks through a sunlit corridor, slow tracking shot, fabric moves naturally, soft directional light, fashion editorial look" works better than "person walking." LTX-2.5 Pro handles complex multi-subject scenes well, so do not simplify the prompt to help the model. Describe what you want.

Note on audio: The model generates audio during the run, but this workflow does not carry it to the output. The downloaded video is picture only.

Note on frame rate: The model generates at 25 fps but the output video is assembled at 30 fps, so playback runs roughly 20% faster than intended. Account for this if timing matters.

LEARN

📹 Videos

• Intro to Floyo

• ComfyUI 101 Free Course ft. Sebastian Kamph

• Floyo 101 for Team Collaboration

✨ Quick links

• Help docs

• LoRA Training guide

• Discover more workflows

USE CASES

🎬 Fashion and Campaign Content
Generate lookbook clips and campaign takes with natural fabric motion, controlled lighting, and camera moves. The pre-filled prompt is built for this.

🎥 Cinematic Previsualization
Block out a shot before committing to a production shoot. Describe the camera, the action, and the environment and get a 1080p reference clip to pitch or plan from.

📱 Short-Form Social Content
Create 5 to 6 second clips for reels, stories, or ads. Switch to 9:16 for vertical formats.

🎨 Motion Design and VFX Reference
Generate motion reference for complex scenes with crowds, fast action, or multi-subject compositions. Pro handles dense scenes better than most open-weights models at this resolution.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• Shot-brief style prompts with subject, action, camera, and lighting

• Fashion, editorial, and cinematic scenes

• Scenes with sharp faces and readable on-screen text

• Complex multi-subject compositions

⚠️ May produce softer results

• Vague one-line prompts with no camera or action direction

• Expecting audio in the output (this workflow outputs picture only)

• Clips longer than what Pro supports (switch to Fast for 20 seconds)

• Expecting 4K (Pro caps at 1080p)

FAQ

What is LTX-2.5 Pro?
LTX-2.5 Pro is the quality-optimized tier of Lightricks' LTX-2.5 video model, released August 2026. It is a 22B-parameter open-weights model that generates video from text at up to 1080p and 25 fps. Pro prioritizes visual fidelity over speed, with strengths in sharp faces, readable on-screen text, and complex scenes.

What is the difference between LTX-2.5 Pro and LTX-2.5 Fast?
Pro is the quality tier, generating at up to 1080p with higher fidelity per frame. Fast is the speed tier, supporting up to 4K resolution and clips up to 20 seconds. Use Pro when visual detail matters most. Use Fast when you need higher resolution, longer clips, or quicker iteration.

Does LTX-2.5 Pro generate audio?
The model generates synchronized audio during the run, but this workflow does not carry it to the output video. The downloaded file is picture only. If you need audio, use a separate sound effects workflow after generating the clip.

Why does the video play faster than expected?
The model generates at 25 fps but the workflow reassembles the video at 30 fps. This makes playback run roughly 20% faster than intended. If precise timing matters for your edit, account for the speed difference in post.

Is LTX-2.5 Pro open source?
LTX-2.5 is released under the LTX-2.x Community License, which allows free use for individuals and organizations under $10M annual revenue. Above that threshold, a commercial license is required. Review the license terms on Hugging Face before using outputs in production.

Can LTX-2.5 Pro generate multishot scenes?
Yes. Native multishot is a core feature of LTX-2.5, meaning the model can generate connected scenes with different camera angles in a single generation while holding character and environment consistent across cuts. Describe the shots in your prompt.

How to run LTX-2.5 Pro online?
You can run LTX-2.5 Pro online through Floyo. No installation, no setup, no API key to wire up. Open the workflow in your browser, write a prompt, and hit run. Free to try.

WHY FLOYO?

Floyo is the only platform with team collaboration for ComfyUI in the browser. You run workflows with no install. You share run history, assets, and models across your team. You pay only when you generate. Floyo supports open-source and closed-source models.

A director runs a take and likes the result. A teammate opens that exact run from shared history and keeps going. No file handoffs. No version confusion.

For studios and enterprise teams, Floyo adds private workspaces, pooled resources, and a team usage dashboard. Other ComfyUI cloud tools run for one person at a time. Floyo runs for the whole team, with transparent per-generation costs.

Ready to try it?
Write a scene brief and run it. A sample prompt is already set.

→ Launch Workflow, Free

Questions? Watch the free course or check the FAQ above.