← Back to brief
ResearchOfficialPreprintarXiv Computer Vision

MagicPrompt: Ultra-Lightweight Prompt Tuning for Video Generation

MagicPrompt is a lightweight framework designed to fine-tune large-scale video diffusion models with extreme parameter efficiency. By combining Attention-Embedded Prompt Tuning and Dual-Space Reward Feedback Optimization, it achieves competitive performance using less than 1% of trainable parameters, significantly lowering training costs. The approach also addresses instability issues in reward-based training for condition-guided tasks.

Why it matters: MagicPrompt enables efficient and stable adaptation of large video diffusion models to new tasks with minimal computational resources.

Full story at: arXiv Computer Vision