LTX 2.3 Pro image-to-video example: Use the provided start image as
This LTX 2.3 Pro image to video example shows Use the provided start image as. It highlights audio-enabled output and camera motion control with 8-second timing · 16:9 · 1080p output.
Prompt breakdown
Text-to-video prompt used to generate this render.
Subject
Use the provided start image as the exact first frame and keep the same old grumpy Toad character, same face, same mushroom cap, same tiny worn outfit, same frying pan, same walking stick, and same ruined battlefield en…
Workflow
Image to video
Camera
Push In
Output
8s · 16:9 · 1080p
Audio
Enabled
Constraints
Image To Video, Audio Enabled, Reference Image
Reference image
Provided
Show full promptHide full prompt
Use the provided start image as the exact first frame and keep the same old grumpy Toad character, same face, same mushroom cap, same tiny worn outfit, same frying pan, same walking stick, and same ruined battlefield environment with broken pipes, smoke, embers, and fire in the background. Create a short live-action fantasy cinematic shot with subtle but expressive motion. Toad stays mostly in place, like a stubborn old survivor who has seen too much. He shifts his weight slightly, tightens his grip on the frying pan, gives a small irritated glance to one side, then looks forward with a deeply unimpressed expression. His face should animate naturally: a little frown, a blink, a tiny scoff, and the attitude of a grumpy veteran who is tired of everyone and everything. His performance should feel dry, deadpan, and funny without becoming cartoonish. Dialogue: in a small old grumbling voice, with perfect dry timing, Toad mutters: “I said I was retired... Apparently evil didn’t get the memo.” Acting direction: the first line is annoyed and tired, like he has already had this conversation too many times. The second line lands with bitter sarcasm and total disbelief. Keep it understated, not exaggerated, not theatrical, not cute. Camera: slightly handheld cinematic close-medium shot, very subtle push-in, as if filmed by a live-action fantasy war film camera operator standing a few steps away. Natural micro-shake, realistic lens breathing, shallow depth of field, grounded framing, no flashy moves. Background action: light environmental movement only — drifting smoke, glowing embers, faint fire flicker, a few falling ashes, subtle heat distortion, maybe a small distant collapse or spark in the ruined battlefield behind him, but nothing that steals focus from Toad. Audio: no music. Only battlefield ambience — soft fire crackle, distant metal creaks, faint rubble settling, low wind through ruins, subtle pipe resonance, drifting ash, small cloth movement, tiny footsteps adjustment, and Toad’s dry grumpy voice clearly audible in the center. Tone: dark live-action fantasy, serious world, dry humor through performance only. Realistic textures, practical atmosphere, emotionally readable, grounded and cinematic, no CGI gloss, no cartoon silliness, no game look.
Why LTX 2.3 Pro fits this shot
Use LTX 2.3 Pro on MaxVideoAI for text-to-video, image-to-video, audio-to-video, extend-video and retake-video workflows with official 1080p/1440p/4K and 24/25/48/50 fps options.
Image input
Audio option
20s max
Key frames



Related examples
View all examples
LTX 2.3 ProLTX 2.3 Pro office image-to-video transition example
This LTX 2.3 Pro example uses image-to-video controls to preserve a scene across a directed office transition with strong frame continuity.
LTX 2.3 ProLTX 2.3 Pro rooftop lightning fashion shot example
This LTX 2.3 Pro page shows a rooftop fashion prompt with storm lighting, neon city atmosphere and cinematic subject isolation.
LTX 2.3 ProVeo 3.1 Fast living room TV commercial example
This Veo 3.1 Fast watch page shows a bright living-room TV commercial prompt with native audio, controlled staging and a 16:9 ad format.
LTX 2.3 ProKling 3 Pro neon street multi-shot example
This Kling 3 Pro example demonstrates a multi-shot neon street sequence with rain reflections, native audio and structured scene anchors.