Mini Sora 社区

 

minisora 开源社区定位为由社区同学自发组织的开源社区（免费不收取任何费用、不割韭菜），minisora 计划探索实现 Sora 的实现路径可发展可能

• 将定期举办Sora的圆桌和社区一起探讨可能性
• 视频生成的现有技术路径探讨

论文共读计划

• Sora 技术报告: Video generation models as world simulators
• DiT: Scalable Diffusion Models with Transformers
• Latte: Latte: Latent Diffusion Transformer for Video Generation
• Coming soon...

相关工作

Diffusion Model

Paper	Links
1) Diffusion Models Beat GANs on Image Synthesis	Paper, Github
2) High-Resolution Image Synthesis with Latent Diffusion Models	Paper, Github
3) Elucidating the Design Space of Diffusion-Based Generative Models	Paper, Github

Diffusion Transformer

Paper	Links
1) UViT: All are Worth Words: A ViT Backbone for Diffusion Models	Paper, Github
2) DiT: Scalable Diffusion Models with Transformers	Paper, Github
3) SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers	Paper, Github
4) FiT: Flexible Vision Transformer for Diffusion Model	Paper, Github

Video Generation

Paper	Links
1) Animatediff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning	Paper, Github
2) I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models	Paper, Github
3) Animatediff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning	Paper, Github
4) Imagen Video: High Definition Video Generation with Diffusion Models	Paper
5) MoCoGAN: Decomposing Motion and Content for Video Generation	Paper
6) Adversarial Video Generation on Complex Datasets	Paper
7) Photorealistic Video Generation with Diffusion Models	Paper
8) VideoGPT: Video Generation using VQ-VAE and Transformers	Paper, Github

Long-context

Paper	Links
1) World Model on Million-Length Video And Language With RingAttention	Paper, Github
2) Ring Attention with Blockwise Transformers for Near-Infinite Context	Paper, Github
3) Extending LLMs' Context Window with 100 Samples	Paper, Github
4) Efficient Streaming Language Models with Attention Sinks	Paper, Github

Mini Sora 微信社区社区交流群

 

现有高质量资料

社区贡献者