Video generation
How to deploy LTX-2 on a GPU cloud
A 18.9B-parameter video generation model. Full specs, license and use cases.
LTX-2 size and hardware requirements
18.9B
Total parameters
Dense (no MoE)
Architecture
BF16
Published precision
42.2 GB
Min VRAM (native)
| Precision | Weight size on disk | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 35.2 GB | 42.2 GB | RTX A6000 | 1 | $0.330/hr |
| FP8 (quantized) | 17.6 GB | 21.1 GB | RTX 4090 | 1 | $0.340/hr |
| INT4 (quantized) | 8.8 GB | 10.5 GB | RTX 4070 Super | 1 | $0.110/hr |
How to run LTX-2
Run LTX-2 with Diffusers (Python)
Generic example using Hugging Face's diffusers library, not from the model's own docs.
from diffusers import DiffusionPipeline
from diffusers.utils import export_to_video
import torch
pipe = DiffusionPipeline.from_pretrained("Lightricks/LTX-2", torch_dtype=torch.bfloat16)
pipe.to("cuda")
frames = pipe("a description of the scene").frames[0]
export_to_video(frames, "output.mp4", fps=24)Run LTX-2 with ComfyUI
Aquanode's ComfyUI template comes with ComfyUI preinstalled. Download Lightricks/LTX-2's checkpoint into the models folder and load it in a workflow; this is a real Aquanode template, but loading this specific checkpoint is a manual step, not a one-click deploy.
Deploy LTX-2 on Aquanode
Aquanode has no one-click deploy template for LTX-2; you install the inference engine yourself with the commands below. Aquanode sells GPU pods billed per second, not a hosted inference API.
- Launch a bare GPU pod sized to the requirement above (1× RTX A6000 or larger).
- Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
- Run the command and connect to the resulting endpoint.
Launch a GPU pod