Paper
Geração de Imagem
DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation
DomainShuttle enables open domain subject-driven text-to-video generation with high fidelity and flexibility across in-domain and cross-domain scenarios through domain-aware modeli…
Hugging Face · Daily Papers
·Nan Chen, Yiyang Cai
·
·▲ 49 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Nan Chen, Yiyang Cai, Rongchang Xie, Junwen Pan, Cheng Chen, Weinan Jia
- 49 upvotes da comunidade
- Temas: text-to-video generation, domain-aware AdaLN, Video-Reference DualRoPE, Cross-Pair Consistent Loss, domain-specific modeling, subject-level spatial modeling
Resumo
Resumo original (em inglês), extraído do paper:
DomainShuttle enables open domain subject-driven text-to-video generation with high fidelity and flexibility across in-domain and cross-domain scenarios through domain-aware modeling and dual RoPE schemes.
// relacionados