# The hand-off

Period: Nov 2024 – Jan 2025 · Era: 2024 · The Great Convergence

December 2024: one image plus a prompt becomes a cast of references plus a prompt.

In one month at the end of 2024, three tools started accepting several reference images at once: a face, an outfit, a location. Instead of hoping a character looked the same in the next shot, you could show the model exactly who and what you meant.

## How it worked

1. Kling 1.6 shipped with first and last frame conditioning and, through Elements, up to four subject images (people, animals, objects, scenes) combined with a prompt; the global rollout landed in January 2025.
2. Pika 2.0 Scene Ingredients let you upload as many reference images as you like for character, object, wardrobe and setting, then prompt the shot.
3. Runway Frames was the pre-echo: an image model built around consistent worlds feeding Gen-3 image-to-video.
4. The consistency toolkit underneath (DreamBooth, LoRA, IP-Adapter, ComfyUI graphs) is what artists reached for whenever the hosted model could not hold a face.

## Why it mattered

Three December releases changed the input contract of the whole industry within a month.

## Tools of the era

- Kling 1.6 Elements (2024): https://klingai.com
- Pika 2.0 Scene Ingredients (2024): https://pika.art
- Runway Frames (2024): https://runway.com/research/introducing-frames
- DreamBooth (2022): https://dreambooth.github.io
- LoRA for diffusion (2022): https://github.com/cloneofsimo/lora
- IP-Adapter (2023): https://github.com/tencent-ailab/IP-Adapter
- ComfyUI (2023): https://github.com/comfyanonymous/ComfyUI

## Example videos and posts

- Kling 1.6 · Kling AI: https://x.com/Kling_ai/status/1869599147046871488
- Scene Ingredients · Pika: https://x.com/pika_labs/status/1867702040656548163
- Runway Frames and Kling Elements · Theoretically Media: https://www.youtube.com/watch?v=7jwSNb4qq_E

## On the timeline

- [Kling 1.6](https://aifilmhistory.org/entry/kling-1-6) (2024-12-19)
- [Veo 2](https://aifilmhistory.org/entry/veo-2) (2024-12)

## Sources

- Kuaishou: multi-image reference: https://ir.kuaishou.com/news-releases/news-release-details/kuaishou-kling-ai-unveils-multi-image-reference-feature-further/
- Pika 2.0 launch: https://venturebeat.com/ai/pika-2-0-launches-in-wake-of-sora-integrating-your-own-characters-objects-scenes-in-new-ai-videos
- Runway Frames: https://runway.com/research/introducing-frames
- IP-Adapter guide: https://stable-diffusion-art.com/ip-adapter/

---
Source: https://aifilmhistory.org/workflows/first-reference-workflows