158 models, and what their licences actually say

Specifications are what each vendor's documentation said on the date we read it. Where a figure could not be sourced, it says so rather than guessing.

Browse by what it makes

Each category has its own page, with a written introduction and a side-by-side comparison of the specs that decide the choice.

Search the directory

158 models

3D assets has no model in this directory. That is a gap in what we have catalogued, not a claim that nothing exists.

Adobe Premiere Pro AI tools (Generative Extend)

Premiere Pro carries a set of Firefly-backed AI features, the best known being Generative Extend, which lengthens a clip's head or tail by generating additional

Editing and post · Adobe

DaVinci Resolve 21 AI tools (Neural Engine)

DaVinci Resolve 21 bundles a large set of Neural Engine AI tools inside a full edit, grade, VFX and audio suite. Version 21 adds AI IntelliSearch for finding pe

Editing and post · Blackmagic Design

Descript Underlord

AI co-editor inside Descript's transcript-based editor that performs editing actions on command: removing filler words, adding captions, generating short clips,

Editing and post · Descript

Google Flow

Google's consumer and prosumer filmmaking app built on Veo 3.1. It wraps generation in a shot-based workflow: text-to-video, Frames to Video, Ingredients to Vid

Editing and post · Google

Kaiber Superstudio

AI video generation and styling tool known for music-video style transformations under the Superstudio interface. Liveness check on 2026-08-14: kaiber.ai still

Editing and post · Kaiber

Luma Modify Video (Ray3.2)

Video-to-video editing mode of Ray3.2. It re-renders existing footage from a natural-language prompt while conditioning on the source, with nine strength preset

Editing and post · Luma AI

OpusClip

Takes long-form video and automatically cuts it into short vertical clips, adding animated captions, reframing to vertical, scoring likely virality and publishi

Editing and post · OpusClip

Pikadditions

Inserts an object or character into existing video footage, matching it to the scene. Exposed as a video-to-video model on the Pika API at a flat per-request pr

Editing and post · Pika

Pikaffects

Preset physical effect transformations applied to an image or an existing video, such as melting, exploding, inflating, crushing or dissolving a subject. Availa

Editing and post · Pika

Pikaswaps

Replaces an object or element in an existing video with a different one while keeping the surrounding footage intact. Exposed as a video-to-video model on the P

Editing and post · Pika

Wan 2.1 VACE (1.3B and 14B)

An all-in-one video creation and editing model built on the Wan 2.1 backbone. It handles reference-to-video, video-to-video restyling, masked inpainting and out

Editing and post · Alibaba Tongyi Lab (Wan)

Adobe Firefly Image Model 5

Adobe's current Firefly image model, announced in public beta at Adobe MAX on 28 October 2025, generating at native 4 MP resolution without an upscale pass. It

Image generation · Adobe

FLUX.1 Kontext [pro] / [max]

Instruction-driven image editing models from the FLUX.1 generation (2025), still exposed as live /flux-kontext-pro and /flux-kontext-max endpoints. They take an