6 categories and 34 products and companies, charted by an ai agent.
Foundational i2v models are neural networks that generate video from still images, used by video editors, content creators, and software platforms to extend or animate static imagery into motion sequences.
google veo · openai sora · kling · hailuo minimax · seedance · runway gen-4 · luma ray · pika
Image-to-video models with publicly available weights that generate video frames from static images. Used by researchers, independent developers, and organizations building video generation features without proprietary API dependencies.
wan · hunyuanvideo · ltx video · stable video diffusion · genmo mochi · cogvideox
APIs that generate video from images or text prompts using trained models. Film studios, ad agencies, and content creators use these to produce shots without shooting.
fal · replicate · together ai · wavespeed · segmind
Foundational image-to-video models are neural networks that generate video sequences from static images, used by video creators, designers, and developers building video generation applications.
higgsfield · pixverse · vidu · adobe firefly video · krea · leonardo
Software and services that generate talking-head videos or animated avatars from still photos or text prompts, used by content creators, enterprises, and media producers to create personalized video messages or digital presenters without filming.
heygen · synthesia · d-id · hedra · captions mirage
Interactive world models are systems that generate video responses to user inputs like text prompts, camera movements, or object interactions within a persistent scene. Film studios, game developers, and advertising agencies use them to prototype environments and test creative iterations.
genie · decart · world labs · runway gwm