LTX 2.3 Pro image-to-video example: street push-in

LTX 2.3 ProImage to video6s9:16Audio

This LTX 2.3 Pro image to video example shows street push-in. It highlights audio-enabled output and camera motion control with 6-second timing · 9:16 · 1080p output.

Prompt

Cinematic medium shot of the same character from the start image dancing hip-hop in a Brooklyn-style street. Keep the exact same character identity, face, hairstyle, bandana, outfit, and proportions. No changes. Maintai…

Show full prompt

Cinematic medium shot of the same character from the start image dancing hip-hop in a Brooklyn-style street. Keep the exact same character identity, face, hairstyle, bandana, outfit, and proportions. No changes. Maintain the same framing and camera angle: frontal medium shot, character centered in the street with brick buildings behind. Action: The character performs a smooth hip-hop groove sequence. Movement style: - grounded hip-hop steps - subtle footwork (side step, weight shift) - natural bounce in the knees - relaxed but controlled arm movement - slight shoulder groove The dance should feel effortless, rhythmic, and confident — not exaggerated, not acrobatic. Expression: Cool, focused, confident. Slight attitude in the eyes, natural charisma. Face remains readable and engaged with the camera. Environment: Brooklyn street with brick buildings, parked cars, and soft urban life. A few people in the background, slightly blurred, walking or standing. Subtle street details (light tags, textures), not overwhelming. Camera: Very slow forward tracking shot or subtle push-in toward the character. Stable cinematic framing. Lighting: Golden hour sunlight hitting the brick buildings. Warm tones, soft shadows, natural highlights on the face. Depth of field: Shallow depth of field, background softly blurred but recognizable. Motion details: - slight motion blur on arms and feet - subtle wind moving hair and hoodie - gentle camera micro-movement for realism Style: High-end streetwear / music video aesthetic (Nike, Aime Leon Dore, NYC vibe). Ultra-realistic, cinematic color grading. Mood: Cool, confident, urban energy, effortless style. Important: - preserve exact identity - keep movements realistic and grounded - no exaggerated tricks or flips - no scene change - smooth continuous single shot

Render details

Workflow

Image-to-video workflow

6-second render in 9:16

Audio-enabled output

Single reference image

Push-in camera move

Controls

Reference image

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

6s

Aspect ratio

9:16

Resolution

1080p

FPS

25

Audio

Enabled

Render cost

$0.47

Created

2026-03-23

Related examples

Recreate

Load this render in the workspace

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