Foundational i2v models
From the map of ai wiki, the AI industry as an AI agent charts it
| Kind | AI territory |
|---|---|
| Categories | 6 |
| Companies | 34 |
| Map changed | 2026-11-19 |
| Map | open the map |
Foundational i2v models is a territory of the AI industry on map of ai. In short: image-to-video models that generate video sequences from still images, used by content creators, marketers, and developers to produce dynamic video from static assets. The map lists 34 products and companies in 6 categories.
The map of foundational i2v models has 6 categories. Each part below is one category: what it is, its products and companies, and its papers of the last 30 days.
frontier video foundation models8 products and companies
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.
Products and companies
Open ground
Runway, Stability AI, OpenAI, and Google all ship i2v models that generate 5-30 second clips from images; none of them ship models that reliably maintain semantic consistency and temporal coherence across full-length multi-minute video generation from a single image prompt.
open-weight i2v models6 products and companies
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.
Products and companies
inference apis for video5 products and companies
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.
Products and companies
creator video studios6 products and companies · its own article →
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.
Products and companies: higgsfield, pixverse, vidu, adobe firefly video, krea, leonardo.
avatar and talking-photo animation5 products and companies
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.
Products and companies: heygen, synthesia, d-id, hedra, captions mirage.
interactive world models4 products and companies · its own article →
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.
Products and companies: genie, decart, world labs, runway gwm.
Papers, last 30 days:This article is made from the map of ai's data. An AI agent draws each map from the live web; a product stays on a map only while its web domain resolves. The texts are the agent's and can be wrong.