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
Cinematic color grading and strong character consistency from reference images.
TrackedOpen-weight model that animates a single still image into a short clip — no text prompts.
TrackedTalking avatar / digital human 6
Mobile-first AI video app — best known for auto-captioning, also does avatar talking videos.
TrackedTurns a photo and text into a lip-synced talking video, plus real-time conversational agents.
TrackedAnimates any photo — photorealistic, illustrated, or non-human — into a speaking character.
TrackedPhotorealistic AI presenter avatars, with lip-sync translation across 175 languages.
TrackedTurns a typed script into a presenter-led video in 160+ languages — no camera or actor needed.
TrackedReal-time, two-way conversational video agents — not a one-way scripted avatar tool.
TrackedText-to-video 18
Commercially-safe video model trained only on licensed content, built into Creative Cloud.
TrackedAlibaba's Wan model line — an open-source Apache 2.0 series plus a newer closed multimodal preview.
TrackedMulti-shot video model built for narrative consistency — subject and style stay stable across cuts.
TrackedGoogle's flagship video model, rated top overall for cinematic quality in independent 2026 roundups.
ListedMiniMax's consumer video model, currently Hailuo 2.3, generating from text or images.
TrackedDiscontinued — London startup's consumer video app shut down Feb 2025; models now owned by NetMind.AI.
TrackedBest-in-class photorealistic human motion, with a built-in multi-shot storyboard tool.
TrackedLightricks' hosted video production platform, built on its own open-source LTX model family.
ListedNot publicly available — Meta's research video model, accessible only via select filmmaker partnerships.
TrackedOpen-source 10B-parameter text-to-video model released under Apache 2.0.
TrackedThe most affordable, effects-rich model in this directory, built for fast social content.
TrackedBeijing startup's video platform with cinema-style camera controls and multi-shot generation.
ListedProduction-grade video model with the widest editing/control toolset in this directory.
TrackedOpen-source video model family for long-form generation, self-hosted rather than API-only.
TrackedDiscontinued — OpenAI's video-and-audio model shut down its app in April 2026, API sunsetting Sept 2026.
TrackedTencent's open-weight video foundation model — over 13B parameters, released with code and weights.
TrackedChinese video model with text, image, and multi-reference generation, rooted in Tsinghua research.
TrackedZhipu AI's open video model family, powering their consumer 'Qingying' product.
Tracked