The AI model field guide

AI models: video, images and creative workflows

Choose a documented capability before choosing a model name. This directory separates video generators, image models and workflow tools. Unknown limits stay visible.

Last verified 2026-10-07

28 models and workflows

Higgsfield

Ad Multiplier

Controlled ad variations

toolNative audio30s max
Higgsfield

Cinema Studio 4.0

Camera, lighting and pacing direction

videoNative audio30s max
Higgsfield

Clipify

Repurposing a YouTube video

tool
Black Forest Labs

FLUX.2

Reference-led image composition

image
Black Forest Labs

FLUX 3 Image

Product and UGC image experiments

image
Black Forest Labs

FLUX 3 Video

Frames, references and continuation

videoNative audio20s max
Google

Gemini Omni Flash

Image and video reference experiments

videoNative audio10s max
Higgsfield

Genjutsu

Motion-preserving video transformation

tool
OpenAI

GPT Image 2.5

Precise edits with an explicit variant choice

image
OpenAI

GPT Image 2

Instruction-led image generation and edits

image
xAI

Grok Video 1.5

Photo-led video exploration

videoNative audio15s max
Ideogram

Ideogram 4.5

Typography-led image workflows

image
Kuaishou

Kling 3.0 Turbo

Short drafts from a starting frame

video15s max
Kuaishou

Kling 3.0

Multi-shot scenes with native sound

videoNative audio15s max
Kling

Kling O1 Image

Literal surreal characters to inspect against your prompt

image
Higgsfield

Marketing Studio

Product-ad production around assets and hooks

videoNative audio15s max
MiniMax

MiniMax H3

Reference-led video at a documented 2K output

videoNative audio15s max
Google

Nano Banana 2

Image iteration before committing to a direction

image
Google

Nano Banana Pro

Deliberate diagrams and designed imagery

image
Recraft

Recraft V4.1

Design-led graphics and brand explorations

image
Runway

Runway Gen-4.5

A separate cinematic generation ecosystem

video
ByteDance

Seedance 2.0

Multimodal reference workflows

videoNative audio15s max
ByteDance

Seedance 2.5

Reference-led stories and selective edits

videoNative audio30s max
ByteDance

Seedream 5.0 Pro

Reasoning-led image briefs

image
Higgsfield

Soul 2.0

A consistent synthetic persona workflow

image
Google

Veo 3.1 Lite

Short audio-video drafts

videoNative audio8s max
Google

Veo 3.1

Short scenes where sound matters

videoNative audio8s max
Wan

Wan 3.0

First/last-frame direction with references

videoNative audio30s max