LTX 2.3 Pro image-to-video example: city camera move

LTX 2.3 ProImage to video10s16:9Audio

This LTX 2.3 Pro image to video example shows city camera move. It highlights audio-enabled output and camera motion control with 10-second timing · 16:9 · 1080p output.

Prompt

Use the provided start image as the first frame and the end image as the final frame anchor. Preserve exact character identity (face, glasses, suit, proportions), bedroom layout, lighting, and object continuity. Scene:…

Show full prompt

Use the provided start image as the first frame and the end image as the final frame anchor. Preserve exact character identity (face, glasses, suit, proportions), bedroom layout, lighting, and object continuity. Scene: a quiet, modest apartment bedroom in the early morning. Soft natural light enters through the curtains. The atmosphere is still, intimate, slightly heavy. Camera: slow cinematic camera movement, very subtle and controlled gentle lateral drift combined with a slight push-in feels like a human operator breathing with the character no abrupt motion, no shake Action: 0:00–0:03 The gorilla lies on his back, staring at the ceiling. He breathes slowly at first. Minimal movement. 0:03–0:06 His breathing becomes heavier, more noticeable in his chest and shoulders. A slight tension appears in his face. Eyes fixed, unfocused. 0:06–0:08 A small shift of the head toward the side (transition toward end frame). His gaze drifts, still empty, lost in thought. 0:08–0:10 He settles into stillness again, breathing heavy but controlled. End frame matches the second image angle. Performance: - strong sense of fatigue and mental weight - distant, empty gaze ("life is hard" feeling) - no exaggerated acting, fully grounded realism - subtle micro-expressions only Environment: - completely quiet room - slight curtain movement from soft air - natural light slowly evolving Motion: real-time only, no slow motion very subtle body movement (chest breathing is key) Audio: - deep, heavy breathing - very soft room tone - distant city ambience (barely audible) - no music Lighting: soft diffused morning light slight variation in light as time passes natural shadows, muted tones Style: cinematic realism, minimalist, introspective 35mm film look, slight grain, soft highlight roll-off shallow depth of field, focus on face and chest movement No text, no subtitles, no logos

Render details

Workflow

Image-to-video workflow

10-second render in 16:9

Audio-enabled output

Single reference image

camera-move

Controls

Reference image

Provided

End frame

Provided

Engine

LTX 2.3 Pro

Use LTX 2.3 Pro on MaxVideoAI for text-to-video, image-to-video, audio-to-video, extend-video and retake-video workflows with Fal’s official 1080p/1440p/4K and 24/25/48/50 fps options.

Image input
Audio option
20s max

Specs

Engine

LTX 2.3 Pro

Mode

Image to video

Duration

10s

Aspect ratio

16:9

Resolution

1080p

FPS

24

Audio

Enabled

Render cost

$0.78

Created

2026-03-20

Related examples

Recreate

Load this render in the workspace

Start from the same prompt and settings, then remix duration, aspect ratio, references, or audio.