xiejunjie524
精选
handdraw-story-video
A tool that converts 7–9 hand-drawn story keyframes into a 35–45 second vertical video with progressive line art and color animation, configurable via JSON and renders with HyperFrames and GSAP.
AI 仓库情报摘要
FR-AI / ANALYSIS为什么值得关注
它展示了精心对齐的小型教师能在视频蒸馏中胜过大型教师，并提供了完全开源发布，包括检查点、训练数据和评估流程。
适合谁使用
- 从事视频生成和扩散模型的研究人员
- 对模型蒸馏与压缩感兴趣的实践者
- 自回归视频架构的开发人员
- 寻求高效视频合成流程的工程师
典型使用场景
- 将大型视频生成模型（如Wan2.1-14B）压缩为更小的学生模型
- 为自回归视频模型的蒸馏技术设定基准
- 以更低计算成本生成高质量视频
- 复现并扩展视频蒸馏的最新成果
项目优势
- 使用1.3B教师即超越以14B教师精炼的基线
- 提供完整的开源资源：代码、检查点、训练数据和评估工具
- 包含基于V-JEPA2特征的教师归一化分布评估流程
- 支持单条和批量推理，命令清晰明确
使用前须知
- 需要较大显存（学生模型至少24GB，原生14B教师需80GB）及128GB系统内存以加载14B教师
- 当前仅针对Wan2.1架构，未验证对其他视频模型的泛化能力
- 评估协议依赖固定提示/种子网格和V-JEPA2编码器，可能无法全面反映视频质量
README 快速开始
DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation
Jiaxing Li1,2*, Kai Zou1*, Cindy Zhou1,3, Kaichen Huang1,2, Junyao Gao1, Zile Wang1,
Yang Liu1, Bin Liu1, Bo An2, Yangguang Li1†
1Riemann Dynamics 2Nanyang Technological University 3Wellington College, UK
*Equal contribution †Corresponding author
DistillAlign aligns and balances the mode-covering and mode-seeking objectives of the multi-stage autoregressive video distillation pipeline — using only a 1.3B DMD teacher, it already surpasses baselines refined with a 14B DMD teacher.
Columns · Wan2.1-1.3B | Self-Forcing | Causal-Forcing | Ours (1.3B teacher) | Ours (14B teacher)
🔥 News
- [2026-07] Initial release: inference code, released checkpoints, training data, and the full teacher-normalized distribution-evaluation pipeline.
🤗 Release Table
All released generators are Wan2.1-1.3B students; the size in each name refers to the teacher used during training.
Checkpoints
| Model | Checkpoint | Description |
|---|---|---|
| Initializer (1.3B teacher) | 🤗 Huggingface | Pre-DMD initializer, trained toward a Wan2.1-T2V-1.3B teacher |
| Initializer (14B teacher) | 🤗 Huggingface | Pre-DMD initializer, trained toward a Wan2.1-T2V-14B teacher |
| Distilled (1.3B teacher) | 🤗 Huggingface | Final joint-distilled generator, Wan2.1-T2V-1.3B DMD teacher |
| Distilled (14B teacher) | 🤗 Huggingface | Final joint-distilled generator, Wan2.1-T2V-14B DMD teacher |
Distillation data (prompts curated from VidProM, 25K samples each):
| Data | Download | Description |
|---|---|---|
| Wan2.1-14B data | 🤗 Huggingface | 25K distillat |
项目描述
DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation
相关仓库与替代方案
根据分类、Topic 和编程语言匹配的相似项目。
bytec-ai
精选
book-video-factory
A portable multi-account short video production skill for books that manages accounts, scripts, images, voiceovers, subtitles, and final exports through a unified workspace.
Krishnagangwal
精选
CS-Fundamentals
A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.