LTX 2 Pro: Advanced Image-to-Video with 4K Motion Control

What this mode does

LTX 2 Pro Image-to-Video (I2V) turns a single reference image plus a prompt into a coherent video. It's built for maximum fidelity: preserve subject identity, add controlled camera/motion, and optionally generate synchronized audio. Use it to animate images with LTX 2 for cinematic results.

Speed profile (Pro)

• Optimized for quality, not raw speed.
• Higher resolutions (1440p-2160p) and 50 FPS increase latency.
• For quick previews, start at 1080p, 6s, 25 FPS; scale up after you lock the look.
• Generation time is typically longer than fast text-to-video generation baselines due to higher step counts and 4K capability.

How Image-to-Video works (I2V mechanism)

• Image conditioning anchors composition and identity from your image_url.
• Your prompt describes motion, atmosphere, and camera moves (e.g., "slow dolly in", "pan right").
• The model preserves key visual details from the image while synthesizing temporally consistent motion.

Retake workflow

Use I2V to create a strong first pass, then refine with targeted edits:

1) Generate your base clip here.

2) Send it to Retake to adjust motion intensity, re-time segments, or refine specific regions without starting over: LTX 2 Retake Video

Inputs

• image_url (required): JPG/PNG/WEBP/... reference image.
• prompt (required): Describe subject, motion, environment, and camera.
• duration: 6 / 8 / 10 seconds.
• resolution: 1080p / 1440p / 2160p.
• aspect_ratio: 16:9.
• fps: 25 or 50.
• generate_audio: true/false (default true).

Recommended settings

• Cinematic look: 25 FPS, 1080p or 1440p, describe subtle camera motion.
• High action: 50 FPS, 6s duration to maximize coherence.
• Final delivery: 2160p (4K) once creative choices are locked.