# Character sheets

Period: Dec 2024 – Jan 2025 · Era: 2025 · The Studio Era

Identity comes from images, not luck.

Make a few views of your character, upload them, and the model keeps them consistent across scenes. This turned the character sheet, long a staple of animation studios, into the first thing an AI filmmaker makes.

## How it worked

1. Generate three or four views of a character in Midjourney or Flux.
2. Load them as Kling Elements and describe the actions and interactions; the model holds the subject across scenes.
3. Generate five-to-ten-second clips per shot and assemble in Premiere or Resolve.
4. Veo 2 (VideoFX) offered cinematographic vocabulary and 4K for the shots that needed polish.

## Why it mattered

The first mainstream tool where identity came from images. The habit of making a character sheet before making a film starts here.

## Tools of the era

- Kling 1.6 Elements (2024): https://klingai.com
- Veo 2 (2024): https://deepmind.google/models/veo/
- Midjourney (2022): https://midjourney.com
- LoRA for diffusion (2022): https://github.com/cloneofsimo/lora
- ComfyUI (2023): https://github.com/comfyanonymous/ComfyUI

## Example videos and posts

- KITSUNE: about 1,700 curated shots · Henry Daubrez: https://x.com/henrydaubrez/status/1879883806947115446
- Behind the scenes of an AI film: The Bridge (Veo 2, Hedra, ElevenLabs) · Theoretically Media: https://www.youtube.com/watch?v=6MRSaaxhz7A
- Consistent realistic characters with a Flux LoRA · Curious Refuge: https://www.youtube.com/watch?v=TdjDK3dSnDY
- The secret to AI character sheets · Theoretically Media: https://www.youtube.com/watch?v=X-rlr3k-2TI

## 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)
- [Kitsune](https://aifilmhistory.org/entry/kitsune) (2025-01)
- [The Bridge](https://aifilmhistory.org/entry/the-bridge-veo-2) (2025-03-24)

## Sources

- Kling character consistency guide: https://kling.ai/quickstart/ai-video-character-consistency
- Veo 2 announcement: https://blog.google/innovation-and-ai/models-and-research/google-labs/video-image-generation-update-december-2024/
- Henry Daubrez interview: https://promptscene.substack.com/p/google-labs-artist-henry-daubrez

---
Source: https://aifilmhistory.org/workflows/multi-image-references