Use cases · image and video

Generate images and video on a GPU of your own.

Run open image and video models in ComfyUI on a dedicated machine, billed per minute. Below: the models people use now, the tools, demos, a one-click deploy, and everything we have written on the subject.

Updated 2026-11-21. Model facts come from the articles linked under each list.

Models people use now

Video models

Two open video families are licensed for use in the EU. HunyuanVideo 1.5 and MiniMax H3 are not: their licenses exclude the EU, so they are left out here.

Alibaba Wan-AIText · image to video

Wan 2.2

T2V and I2V at 14B active (27B total), a 5B TI2V model, and Animate for character motion.

Apache 2.0 · allowed in the EU

LightricksVideo · audio

LTX-2.5

A 22B DiT with a Gemma 4 12B text encoder that generates sound with the clip. One owner reported about 70 seconds for a 5-second 768x512 clip on a DGX Spark.

LTX-2.x Community License · free under $10M revenue

Source: Video generation guide, 7 November 2026, with sizes, licenses and links to each model card.

Models people use now

Image models

The top of Artificial Analysis's open-weights image board on 7 November 2026, plus the strongest models you can use commercially at any company size.

QwenText to image

Qwen-Image-2.1

7B DiT, ranked first among open-weight image models (Elo 1045).

Qwen Research License · non-commercial

Black Forest LabsText to image

FLUX 3 Image Klein

5.6B with a Qwen3-VL-4B encoder; about 4 seconds per 1 MP image on an RTX 5090, per BFL.

FLUX Kommunity License · free under $5M revenue

Alibaba TongyiText to image

Z-Image-Turbo

6B and fast; the pick when you need an Apache 2.0 license at any company size.

Apache 2.0 · commercial use

Source: Local image models compared, 7 November 2026, with sizes, licenses and links to each model card.

Tools

What runs them.

ComfyUIOne-click preset

ComfyUI

The node editor most image and video workflows are shared in. Checkpoints, custom nodes and outputs live in /workspace/comfy and survive a stop.

Python

Diffusers

Hugging Face's library for running the same models from a script or a notebook. Install it with pip in the JupyterLab preset.

Reference setup

NVIDIA's ComfyUI playbook

NVIDIA's own steps for installing ComfyUI on a DGX Spark.

See it running

Demos and walkthroughs.

From the model makers and the ComfyUI team. A video loads from YouTube (youtube-nocookie.com) only when you press play.

Wan 2.2
Wan 2.2, the generative AI model built for the language of film Alibaba Cloud on YouTube
LTX-2.5
LTX-2.5: The Open World Model the World Builds On LTX_io (Lightricks) on YouTube
FLUX 3 Klein in ComfyUI
FLUX 3 Klein is Now in ComfyUI: Open Weights & Native 4K ComfyUI on YouTube
Z-Image-Turbo in ComfyUI
Z-Image Turbo in ComfyUI - Local and Cloud ComfyUI on YouTube
ComfyUI basics
ComfyUI Tutorial for Beginners: Full Node Graph Basics (2026) ComfyUI on YouTube
ComfyUI on a DGX Spark
Generate Visual AI Faster with ComfyUI on NVIDIA DGX Spark PNY Pro on YouTube

Deploy

Start in one click.

A whole machine for yourself, billed per minute from prepaid credit. Terminate when you are done and billing ends.

ComfyUIOne click

ComfyUI on a DGX Spark

128 GB of memory, so pipelines that peak above 100 GB fit. Opens in your browser through an SSH tunnel.

Preset · 1 × DGX Spark

JupyterOne click

JupyterLab on a DGX Spark

For Diffusers scripts and notebooks on the same 128 GB machine.

Preset · 1 × DGX Spark

NVIDIAInstall yourself

RTX 5090, Ubuntu 24.04

Faster per clip: reports put the RTX 5090 2.4 to 5.5 times ahead of a Spark on the same video job, within 32 GB. You install ComfyUI yourself.

x86 · 32 GB GDDR7

Model library · Pricing

Guides and articles

Go deeper.