Deploy LTX-2
VideoLTX-2 from Lightricks is a 19B parameter video generation model supporting up to 4K resolution with audio. The distilled variant generates in 8 steps, while dev variants offer maximum quality with custom workflow control.
Deploy LTX-2 in minutes
Starting at $0.66/hr on dedicated GPU
Available Variants (3)
| Model | GPU | VRAM | Price | Action |
|---|---|---|---|---|
LTX-2 19B Distilled Distilled (Recommended) | A100 80GB PCIe | 80 GB | $1.85/hr | Deploy |
LTX-2 19B Dev FP8 Dev FP8 (High Quality) | A100 80GB PCIe | 80 GB | $1.85/hr | Deploy |
LTX-2 19B Dev FP4 Dev FP4 (Low VRAM) | RTX A6000 | 48 GB | $0.66/hr | Deploy |
Prices include the service fee. Charges follow actual running time.
Requirements
ModelPilot assigns 48–80GB cloud GPUs across the listed variants. Actual local VRAM requirements vary with model variant, precision, quantization, resolution, and workflow settings.
On ModelPilot, deploy on a dedicated cloud GPU (up to 80GB VRAM) starting at $0.66/hr with no setup required.
Use Cases
- ✓4K video generation
- ✓Video with synchronized audio
- ✓Professional video production
- ✓High-resolution content creation
Related Models
Frequently Asked Questions
How much GPU memory is allocated for LTX-2?
The listed ModelPilot variants use 48–80GB cloud GPUs. Local memory needs vary with the variant, precision, quantization, and workflow settings.
How much does it cost to run LTX-2?
Starting at $0.66/hr on a dedicated GPU. Charges are calculated from actual running time, with auto-stop when credits run out.
How long does LTX-2 take to deploy?
Video models typically take 15–30 minutes for first deployment (model download + setup). Subsequent starts are faster.
Can I run LTX-2 on my local GPU?
It depends on the selected variant, precision, quantization, and workflow settings. Compare the variants below with your available VRAM; the table shows ModelPilot's cloud GPU allocation, not a universal local minimum.
Ready to deploy LTX-2?
Pick your GPU and have it running in minutes. No infrastructure setup required.