Directory

Every AI video model, one short profile each

A directory of 26 AI video generation models — text-to-video, image-to-video, and talking-avatar models, with a short factual profile for each.

Text-to-video 18

Adobe Firefly Video

Adobe

Commercially-safe video model trained only on licensed content, built into Creative Cloud.

Tracked

Alibaba Wan (Wanxiang)

Alibaba (Tongyi Lab)

Alibaba's Wan model line — an open-source Apache 2.0 series plus a newer closed multimodal preview.

Tracked

ByteDance Seedance

ByteDance

Multi-shot video model built for narrative consistency — subject and style stay stable across cuts.

Tracked

Google Veo 3.1 (Flow)

Google DeepMind

Google's flagship video model, rated top overall for cinematic quality in independent 2026 roundups.

Listed

Hailuo AI (MiniMax)

MiniMax

MiniMax's consumer video model, currently Hailuo 2.3, generating from text or images.

Tracked

Haiper AI

Haiper (tech now owned by NetMind.AI)

Discontinued — London startup's consumer video app shut down Feb 2025; models now owned by NetMind.AI.

Tracked

Kling 3.0

Kuaishou

Best-in-class photorealistic human motion, with a built-in multi-shot storyboard tool.

Tracked

LTX Video / LTX Studio

Lightricks

Lightricks' hosted video production platform, built on its own open-source LTX model family.

Listed

Meta Movie Gen

Meta (Meta FAIR)

Not publicly available — Meta's research video model, accessible only via select filmmaker partnerships.

Tracked

Mochi 1

Genmo

Open-source 10B-parameter text-to-video model released under Apache 2.0.

Tracked

Pika 2.5

Pika

The most affordable, effects-rich model in this directory, built for fast social content.

Tracked

PixVerse

AIsphere

Beijing startup's video platform with cinema-style camera controls and multi-shot generation.

Listed

Runway Gen-4.5

Runway

Production-grade video model with the widest editing/control toolset in this directory.

Tracked

SkyReels

Skywork AI

Open-source video model family for long-form generation, self-hosted rather than API-only.

Tracked

Sora (Sora 2)

OpenAI

Discontinued — OpenAI's video-and-audio model shut down its app in April 2026, API sunsetting Sept 2026.

Tracked

Tencent Hunyuan Video

Tencent

Tencent's open-weight video foundation model — over 13B parameters, released with code and weights.

Tracked

Vidu

Shengshu Technology

Chinese video model with text, image, and multi-reference generation, rooted in Tsinghua research.

Tracked

Zhipu CogVideoX

Zhipu AI (Z.ai)

Zhipu AI's open video model family, powering their consumer 'Qingying' product.

Tracked