Directory
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.
Image-to-video (2)
Talking avatar / digital human (6)
NOCAP, Inc.
Mobile-first AI video app — best known for auto-captioning, also does avatar talking videos.
D-ID
Turns a photo and text into a lip-synced talking video, plus real-time conversational agents.
Hedra Labs
Animates any photo — photorealistic, illustrated, or non-human — into a speaking character.
HeyGen
Photorealistic AI presenter avatars, with lip-sync translation across 175 languages.
Synthesia
Turns a typed script into a presenter-led video in 160+ languages — no camera or actor needed.
Tavus
Real-time, two-way conversational video agents — not a one-way scripted avatar tool.
Text-to-video (18)
Adobe
Commercially-safe video model trained only on licensed content, built into Creative Cloud.
Alibaba (Tongyi Lab)
Alibaba's Wan model line — an open-source Apache 2.0 series plus a newer closed multimodal preview.
ByteDance
Multi-shot video model built for narrative consistency — subject and style stay stable across cuts.
Google DeepMind
Google's flagship video model, rated top overall for cinematic quality in independent 2026 roundups.
MiniMax
MiniMax's consumer video model, currently Hailuo 2.3, generating from text or images.
Haiper (tech now owned by NetMind.AI)
Discontinued — London startup's consumer video app shut down Feb 2025; models now owned by NetMind.AI.
Kuaishou
Best-in-class photorealistic human motion, with a built-in multi-shot storyboard tool.
Lightricks
Lightricks' hosted video production platform, built on its own open-source LTX model family.
Meta (Meta FAIR)
Not publicly available — Meta's research video model, accessible only via select filmmaker partnerships.
Genmo
Open-source 10B-parameter text-to-video model released under Apache 2.0.
Pika
The most affordable, effects-rich model in this directory, built for fast social content.
AIsphere
Beijing startup's video platform with cinema-style camera controls and multi-shot generation.
Runway
Production-grade video model with the widest editing/control toolset in this directory.
Skywork AI
Open-source video model family for long-form generation, self-hosted rather than API-only.
OpenAI
Discontinued — OpenAI's video-and-audio model shut down its app in April 2026, API sunsetting Sept 2026.
Tencent
Tencent's open-weight video foundation model — over 13B parameters, released with code and weights.
Shengshu Technology (生数科技)
Chinese video model with text, image, and multi-reference generation, rooted in Tsinghua research.
Zhipu AI (Z.ai)
Zhipu AI's open video model family, powering their consumer 'Qingying' (清影) product.