# Ingredients

Period: Oct – Dec 2025 · Era: 2025 · The Studio Era

Three vendors converge on the same input contract in ten weeks.

Within ten weeks, the big three video tools converged on the same idea: give the model ingredients (a few images, a clip, a sound) and get back a multi-shot scene with its own audio. One model, many inputs, one coherent result.

## How it worked

1. Veo 3.1 Ingredients to Video: up to three reference images (character, object, scene, style), now with audio; Frames to Video for first and last frame; Extend to chain past a minute.
2. Storyboards in Nano Banana Pro (fourteen references, identity for five subjects, real text) become first frames.
3. Kling O1, the first unified multimodal video model: seven simultaneous inputs, `@Element1 / @Image1` prompt syntax, prompt-driven editing of uploaded video.
4. Runway Gen-4.5 with native audio and minute-long multi-shot generation; Wan 2.6 reference-to-video where a clip carries appearance and voice.
5. Node canvases go mainstream (Runway Workflows, Freepik Spaces, Krea Nodes) and open weights keep pace: LTX-2 with native audio, HunyuanVideo 1.5 on a single 4090.
6. Use the image model as a coverage engine: generate every angle of a scene in Nano Banana Pro before touching a video model, then animate only the frames you would actually cut to (blizaine, Framer).
7. Let the language model write the prompts, five self-contained shots at a time, each written as if the video model has no memory of the last (PJ Ace).
8. Cut hard between only the beats that matter: short clips and jump cuts read as intent and sidestep long-clip drift (Framer).
9. Bolt open-source voice cloning (E2/F5-TTS) onto the stack for dialogue the video model cannot deliver.

## Why it mattered

Kling, Runway and Google converged on images plus video plus audio in, multi-shot video with native audio out.

## Tools of the era

- Veo 3.1 (Ingredients to Video) (2025): https://deepmind.google/models/veo/
- Nano Banana Pro (2025): https://gemini.google
- Kling O1 (2025): https://klingai.com
- Runway Gen-4.5 (2025): https://runway.com
- Wan 2.6 (2025): https://www.alibabacloud.com
- LTX-2 (2026): https://ltx.io
- Marble (2025): https://www.worldlabs.ai
- Genie 3 (2025): https://deepmind.google
- E2/F5-TTS (2024): https://github.com/SWivid/F5-TTS

## Example videos and posts

- AI film masterclass and cost breakdown: Planet Hell (Veo 3.1, Sora 2 remix) · Theoretically Media: https://www.youtube.com/watch?v=PIAyiStv4uc
- How to make a professional AI animated film · Curious Refuge: https://www.youtube.com/watch?v=aVfawxDj6uw
- The Nano Banana of AI video: Kling O1 · Theoretically Media: https://www.youtube.com/watch?v=TmdObmkpfyA
- Nano Banana Pro angles, Veo 3.1, open-source voice cloning · Blaine Brown: https://x.com/blizaine/status/1993698054394781925
- Replacing a live-action ad campaign: full process · PJ Ace: https://x.com/PJaccetturo/status/1979215033172127798
- A boxing anime with Nano Banana Pro and Sora · Framer: https://x.com/Framer_X/status/1991621968098210189
- Jump cuts: only show what matters · Framer: https://x.com/Framer_X/status/1979227310734872846

## On the timeline

- [Veo 3.1](https://aifilmhistory.org/entry/veo-3-1) (2025-10-14)
- [Nano Banana Pro (Gemini 3 Pro Image)](https://aifilmhistory.org/entry/nano-banana-pro) (2025-11-20)
- [Runway Gen-4.5](https://aifilmhistory.org/entry/runway-gen4-5) (2025-12)
- [Kling 2.6](https://aifilmhistory.org/entry/kling-2-6) (2025-12-03)
- [Wan 2.6](https://aifilmhistory.org/entry/wan-2-6) (2025-12-16)
- [LTX-2](https://aifilmhistory.org/entry/ltx-2) (2025-10-23)
- [Genie 3](https://aifilmhistory.org/entry/genie-3) (2025-08)
- [DRIFT SPLIT](https://aifilmhistory.org/entry/drift-split) (2025-10-03)

## Sources

- Veo 3.1 in Flow: https://blog.google/innovation-and-ai/products/veo-updates-flow/
- Kling O1: https://ir.kuaishou.com/news-releases/news-release-details/kling-o1-launches-worlds-first-unified-multimodal-video-model-0
- Runway Gen-4.5: https://runway.com/research/introducing-runway-gen-4.5
- Nano Banana Pro: https://blog.google/innovation-and-ai/products/nano-banana-pro/
- Wan 2.6: https://www.alibabacloud.com/blog/alibaba-unveils-wan2-6-series-enabling-everyone-to-star-in-videos_602742
- Ad Age on the Teriyaki Madness campaign: https://adage.com/technology/ai/aa-ai-ad-of-the-week-teriyaki-madness/
- Curious Refuge: professional AI animated film: https://www.youtube.com/watch?v=aVfawxDj6uw

---
Source: https://aifilmhistory.org/workflows/ingredients-and-omni-models