Steadicam night-market walk (LTX-2, local)
What they did
A 15-second Steadicam prompt moving through a Southeast Asian night market, run locally on LTX-2.
How it went
The creator's settings: ltx-2-19b-dev-fp8, 1280x720, 24fps, 15 seconds on an RTX 5090. About 40s to generate, then a 2x upscale.
Copy prompt
Steadicam walking shot, 15 seconds. Moving through a bustling outdoor night market in Southeast Asia. Food stalls with hanging lights, smoke rising from grills, colorful ingredients on display. Camera passes close to a vendor flipping noodles in a wok with visible flames. Shallow focus pulls between stalls. Warm tungsten lighting mixed with neon signs.Prompt by @RafaCrackYT on X, quoted with credit; the example clip lives on their post.
Worth knowing
- Price: unknown
- Status: sourced. We have not run this ourselves yet (no "Tested" badge).
- Quality bar (computed by code): 4/5 (primary source ✓, reproducible ✓, new ✓, example output ✗, safe ✓)
The best new AI video workflows and prompts, weekly.
Related
▶ example at sourceLTX Video on fal
Lightricks' open LTX Video model on fal. It's one of the cheapest hosted options, at a flat per-video price.
▶ demo at sourceLTX-2 on fal
Lightricks' LTX-2 Pro on fal: text-to-video with audio from 1080p up to 2160p, billed per second by resolution.
▶ demo at sourceLTX-2 on GitHub
Lightricks' official Python inference package and LoRA trainer for LTX-2, its open audio-video model.
Top-down pastel domino spiral (LTX 2.5 Pro)
A satisfying top-down push-in prompt with hundreds of pastel dominoes toppling in slow motion.
▶ example at sourceMaestro
A fully local video, image and music studio on the WanGP pipeline. Its director mode plans a whole music video or short from one prompt.
▶ example at sourcelanshu-awesome-ai-video-kit
A Chinese-language kit from enterprise video projects: hundreds of prompts across 15 models, Claude skills and methodology notes.