MIMIX

Mohamed bin Zayed University of Artificial Intelligence
arXiv arXiv GitHub Code YouTube Video

🎯 Abstract

Imagine Mr. Bean stepping into Tom & Jerry

Can we generate videos where characters interact naturally across different worlds? We study inter-character interaction in text-to-video generation, where the key challenge is to preserve each character's identity and behaviors while enabling coherent cross-context interaction. This is difficult because characters may have ⚡ never coexisted and because mixing styles often causes 🎨 style delusion, where realistic characters appear cartoonish or vice versa. We introduce a framework that tackles these issues with Cross-Character Embedding (CCE), which learns identity and behavioral logic across multimodal sources, and Cross-Character Augmentation (CCA), which enriches training with synthetic co-existence and mixed-style data. Together, these techniques allow natural interactions between previously uncoexistent characters without losing stylistic fidelity. Experiments on a curated benchmark of cartoons and live-action series with 10 characters show clear improvements in identity preservation, interaction quality, and robustness to style delusion, enabling new forms of generative storytelling.

Mr. Bean appears cartoonish.

Ice Bear appears realistic

Style Delusion Examples

🎬 More Results

Gallery

👥 Multi-Character Comparison

✨ Ours
🎬 Skyreel-A2

👤 Single-character Comparison

✨ Ours
🎬 Skyreel
🎨 Wan-I2V
💫 DreamVideo
🎥 VideoBooth

📚 Citation

BibTeX
@article{mimix2025,
  title   = {Character Mixing for Video Generation},
  author  = {Tingting Liao, Chongjian Ge, Guangyi Liu, Hao Li, Yi Zhou}, 
  year    = {2025}
  eprint       = {2510.05093},
  archivePrefix= {arXiv},
  primaryClass = {cs.CV},
  note         = {arXiv preprint}
}

If you find our work useful in your research, please consider citing our paper.