SMD:多模态蒸馏框架 一套蒸馏加速框架,让小模型能以极短的生成路径快速学会大模型的效果,适用于AI绘画、AI视频、AI语音等多模态场景。 应用 SMD 之后,AI模型只需要经过 4 步左右的计算就能生成细节逼真的高质量图片与视频,生成效率比传统需要几十步计算的模型有了明显提升。而且这项技术通用性很强,不仅能用于图片生成与编辑,还全面适配了 3D 物体建模、长视频生成以及音视频同步生成等多种复杂的多模态任务。 模型:huggingface.co/zjwfufu/SMD Github:github.com/zjwfufu/SMD 项目地址:zjwfufu.github.io/SMD-Page/
Excited to introduce Simplified Matching Distillation (SMD) for few-step diffusion🧵 No auxiliary score model. No adversarial training. No generator modification. You will get: • Photorealistic appearance • High-quality dynamics • Memory-efficient training • Mode covering with diverse outputs SMD works well across images, video, joint audio–video, and 3D gen, validated across model scales up to 33B parameters. Besides, SMD supports: - Multi-teacher capability merging (like OPD in LLM) - Cross-model capability transfer - Bidirectional teacher to causal distillation Full release. Paper, code, model and data. Project Page: zjwfufu.github.io/SMD-Page/ Paper: arxiv.org/abs/2610.18472 Code: github.com/zjwfufu/SMD Model Card & Data: huggingface.co/zjwfufu/SMD Demo Video 👇
查看被引用的帖子




