---
title: "AI models: video, images and creative workflows"
url: https://whatsthatmodel.com/models/
last_updated: 2026-10-07
language: en
---


# 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.

28 models and workflows


## Ad Multiplier↗

Controlled ad variations


Official Higgsfield preview: https://cdn.higgsfield.ai/cinema_studio_40_creative_controls/f86bd18a-e233-4d3f-bc1c-2e5c08c02c69.mp4


## Cinema Studio 4.0↗

Camera, lighting and pacing direction


## Clipify↗

Repurposing a YouTube video


## FLUX.2↗

Reference-led image composition


## FLUX 3 Image↗

Product and UGC image experiments


Video: https://cdn.sanity.io/files/s479xw3z/production/34c02e0395aebcec48812b1ca175dc7faa1e77fe.mp4


## FLUX 3 Video↗

Frames, references and continuation


Video: https://static.higgsfield.ai/gemini-omni/examples/example-output-1-mini.mp4


## Gemini Omni Flash↗

Image and video reference experiments


Video: https://static.higgsfield.ai/genjutus-fixes/hero/itemv.mp4


## Genjutsu↗

Motion-preserving video transformation


## GPT Image 2.5↗

Precise edits with an explicit variant choice


## GPT Image 2↗

Instruction-led image generation and edits


Video: https://static.higgsfield.ai/grok-imagine-1.5/hero-mini.mp4


## Grok Video 1.5↗

Photo-led video exploration


## Ideogram 4.5↗

Typography-led image workflows


Video: https://d28lhcrx5qdowv.cloudfront.net/media/explore/media/a8482c00a810bf05f4264db8ac3ad63847b37998d258f931588e963fa8eb4435-video.mp4


## Kling 3.0 Turbo↗

Short drafts from a starting frame


Video: https://static.higgsfield.ai/kling-3/features/feature-3.mp4


## Kling 3.0↗

Multi-shot scenes with native sound


## Kling O1 Image↗

Literal surreal characters to inspect against your prompt


Video: https://static.higgsfield.ai/ms-intro/hero-carousel/product.mp4


## Marketing Studio↗

Product-ad production around assets and hooks


Video: https://d28lhcrx5qdowv.cloudfront.net/media/explore/media/c4d27237ec0cc455ecdfbfdec058e8c3dc052bd7f34e1433d712dd01ef69fd50-video.mp4


## MiniMax H3↗

Reference-led video at a documented 2K output


## Nano Banana 2↗

Image iteration before committing to a direction


## Nano Banana Pro↗

Deliberate diagrams and designed imagery


## Recraft V4.1↗

Design-led graphics and brand explorations


## Runway Gen-4.5↗

A separate cinematic generation ecosystem


Video: https://static.higgsfield.ai/seedance-2.0-v2/examples-4k/1-mini.mp4


## Seedance 2.0↗

Multimodal reference workflows


Video: https://static.higgsfield.ai/seedance-2.5/v2/hero/video-3.mp4?v=20260807


## Seedance 2.5↗

Reference-led stories and selective edits


## Seedream 5.0 Pro↗

Reasoning-led image briefs


## Soul 2.0↗

A consistent synthetic persona workflow


## Veo 3.1 Lite↗

Short audio-video drafts


Video: https://static.higgsfield.ai/veo31/slide1.mp4


## Veo 3.1↗

Short scenes where sound matters


Video: https://d28lhcrx5qdowv.cloudfront.net/media/explore/media/a022d4de4edead66bb7ec9f2df05fc0ab6e86bf2950085e0001e13977c91d9a8-video.mp4


## Wan 3.0↗

First/last-frame direction with references


## Relevant links and sources

- [Home](https://whatsthatmodel.com/)
- [Higgsfield Ad Multiplier↗  Controlled ad variations  toolNative audio30s max](https://whatsthatmodel.com/models/ad-multiplier/)
- [Official example · Higgsfield Ad Multiplier page](https://whatsthatmodel.com/go/official-ad-multiplier?pt=index&pos=examples)
- [Higgsfield Cinema Studio 4.0↗  Camera, lighting and pacing direction  videoNative audio30s max](https://whatsthatmodel.com/models/cinema-studio-4-0/)
- [Official example · Higgsfield Cinema Studio 4.0 page](https://whatsthatmodel.com/go/official-cinema-studio-4-0?pt=index&pos=examples)
- [03 / AI MODEL      Higgsfield Clipify↗  Repurposing a YouTube video  tool](https://whatsthatmodel.com/models/clipify/)
- [Black Forest Labs FLUX.2↗  Reference-led image composition  image](https://whatsthatmodel.com/models/flux-2/)
- [Official example · Higgsfield FLUX.2 page](https://whatsthatmodel.com/go/official-flux-2?pt=index&pos=examples)
- [ORIGINAL AI IMAGE / N=1      Black Forest Labs FLUX 3 Image↗  Product and UGC image experiments  image](https://whatsthatmodel.com/models/flux-3-image/)
- [Black Forest Labs FLUX 3 Video↗  Frames, references and continuation  videoNative audio20s max](https://whatsthatmodel.com/models/flux-3-video/)
- [Official example · Higgsfield FLUX 3 Video page](https://whatsthatmodel.com/go/official-flux-3-video?pt=index&pos=examples)
- [Google Gemini Omni Flash↗  Image and video reference experiments  videoNative audio10s max](https://whatsthatmodel.com/models/gemini-omni-flash/)
- [Official example · Higgsfield Gemini Omni Flash page](https://whatsthatmodel.com/go/official-gemini-omni-flash?pt=index&pos=examples)
- [Higgsfield Genjutsu↗  Motion-preserving video transformation  tool](https://whatsthatmodel.com/models/genjutsu/)
- [Official example · Higgsfield Genjutsu page](https://whatsthatmodel.com/go/official-genjutsu?pt=index&pos=examples)
- [OpenAI GPT Image 2.5↗  Precise edits with an explicit variant choice  image](https://whatsthatmodel.com/models/gpt-image-2-5/)
- [Official example · Higgsfield GPT Image 2.5 page](https://whatsthatmodel.com/go/official-gpt-image-2-5?pt=index&pos=examples)
- [ORIGINAL AI IMAGE / N=1      OpenAI GPT Image 2↗  Instruction-led image generation and edits  image](https://whatsthatmodel.com/models/gpt-image-2/)
- [xAI Grok Video 1.5↗  Photo-led video exploration  videoNative audio15s max](https://whatsthatmodel.com/models/grok-video-1-5/)
- [Official example · Higgsfield Grok Video 1.5 page](https://whatsthatmodel.com/go/official-grok-video-1-5?pt=index&pos=examples)
- [Ideogram Ideogram 4.5↗  Typography-led image workflows  image](https://whatsthatmodel.com/models/ideogram-4-5/)
- [Official example · Higgsfield Ideogram 4.5 page](https://whatsthatmodel.com/go/official-ideogram-4-5?pt=index&pos=examples)
- [Kuaishou Kling 3.0 Turbo↗  Short drafts from a starting frame  video15s max](https://whatsthatmodel.com/models/kling-3-0-turbo/)
- [Official example · Higgsfield Kling 3.0 Turbo page](https://whatsthatmodel.com/go/official-kling-3-0-turbo?pt=index&pos=examples)
- [Kuaishou Kling 3.0↗  Multi-shot scenes with native sound  videoNative audio15s max](https://whatsthatmodel.com/models/kling-3-0/)
- [Official example · Higgsfield Kling 3.0 page](https://whatsthatmodel.com/go/official-kling-3-0?pt=index&pos=examples)
- [ORIGINAL AI IMAGE / N=1      Kling Kling O1 Image↗  Literal surreal characters to inspect against your prompt  image](https://whatsthatmodel.com/models/kling-o1-image/)
- [Higgsfield Marketing Studio↗  Product-ad production around assets and hooks  videoNative audio15s max](https://whatsthatmodel.com/models/marketing-studio/)
- [Official example · Higgsfield Marketing Studio page](https://whatsthatmodel.com/go/official-marketing-studio?pt=index&pos=examples)
- [MiniMax MiniMax H3↗  Reference-led video at a documented 2K output  videoNative audio15s max](https://whatsthatmodel.com/models/minimax-h3/)
- [Official example · Higgsfield MiniMax H3 page](https://whatsthatmodel.com/go/official-minimax-h3?pt=index&pos=examples)
- [Google Nano Banana 2↗  Image iteration before committing to a direction  image](https://whatsthatmodel.com/models/nano-banana-2/)
- [Official example · Higgsfield Nano Banana 2 page](https://whatsthatmodel.com/go/official-nano-banana-2?pt=index&pos=examples)
- [PRO REQUEST / NANO BANANA 2 BACKEND      Google Nano Banana Pro↗  Deliberate diagrams and designed imagery  image](https://whatsthatmodel.com/models/nano-banana-pro/)
- [Recraft Recraft V4.1↗  Design-led graphics and brand explorations  image](https://whatsthatmodel.com/models/recraft-v4-1/)
- [Official example · Higgsfield Recraft V4.1 page](https://whatsthatmodel.com/go/official-recraft-v4-1?pt=index&pos=examples)
- [21 / AI MODEL      Runway Runway Gen-4.5↗  A separate cinematic generation ecosystem  video](https://whatsthatmodel.com/models/runway-gen-4-5/)
- [ByteDance Seedance 2.0↗  Multimodal reference workflows  videoNative audio15s max](https://whatsthatmodel.com/models/seedance-2-0/)
- [Official example · Higgsfield Seedance 2.0 page](https://whatsthatmodel.com/go/official-seedance-2-0?pt=index&pos=examples)
- [ByteDance Seedance 2.5↗  Reference-led stories and selective edits  videoNative audio30s max](https://whatsthatmodel.com/models/seedance-2-5/)
- [Official example · Higgsfield Seedance 2.5 page](https://whatsthatmodel.com/go/official-seedance-2-5?pt=index&pos=examples)
- [ORIGINAL AI IMAGE / N=1      ByteDance Seedream 5.0 Pro↗  Reasoning-led image briefs  image](https://whatsthatmodel.com/models/seedream-5-0-pro/)
- [ORIGINAL AI IMAGE / N=1      Higgsfield Soul 2.0↗  A consistent synthetic persona workflow  image](https://whatsthatmodel.com/models/soul-2-0/)
- [26 / AI MODEL      Google Veo 3.1 Lite↗  Short audio-video drafts  videoNative audio8s max](https://whatsthatmodel.com/models/veo-3-1-lite/)
- [Google Veo 3.1↗  Short scenes where sound matters  videoNative audio8s max](https://whatsthatmodel.com/models/veo-3-1/)
- [Official example · Higgsfield Veo 3.1 page](https://whatsthatmodel.com/go/official-veo-3-1?pt=index&pos=examples)
- [Wan Wan 3.0↗  First/last-frame direction with references  videoNative audio30s max](https://whatsthatmodel.com/models/wan-3-0/)
- [Official example · Higgsfield Wan 3.0 page](https://whatsthatmodel.com/go/official-wan-3-0?pt=index&pos=examples)
