Video generation

Text- and image-to-video diffusion. The hosted models lead on length, motion and consistency; open models (HunyuanVideo, Wan, LTX-Video, Mochi) bring generation to local GPUs, increasingly in real time on consumer cards.

Providers

The leading hosted services — sign up and use them via app or API.

Provider	From	Strengths	Access
Sora 2	OpenAI	Long, coherent shots; audio	App · API
Veo 3	Google	High fidelity, native audio	App · API
Gen-4	Runway	Creative control, editing suite	App · API
Dream Machine	Luma	Fast, expressive motion	App · API
Kling	Kuaishou	Strong motion & realism	App · API
Seedance	ByteDance	Multi-shot, fast	API
Hailuo	MiniMax	Cinematic, cheap	App · API

Open-source tools

Run these yourself on a local or rented GPU. Open weights are free to use, private, and finetunable.

HunyuanVideo

Tencent's open 13B video model — strong open-weight quality.

modelopen

Wan

Alibaba's open text/image-to-video family, widely used in ComfyUI.

modelopen

LTX-Video

Lightricks' fast open model — near real-time on a single GPU.

modelfast

Mochi 1

Genmo's open, high-motion diffusion model.

modelopen

CogVideoX

Zhipu/THUDM open text-to-video models in several sizes.

modelopen

Open-Sora

An open reproduction of the Sora recipe, training code included.

modelopen

Self-Forcing

Real-time autoregressive video generation research + code.

realtimeresearch

ComfyUI

The same node UI runs most open video models end-to-end.

What you need to run it

See GPU prices to buy a card, hosting to rent one by the hour, and GPU programming to understand the libraries underneath. VRAM is the deciding factor — check each tool's model card for its memory needs.