Infinite Image Generation
1개 벤치마크 · 논문 2편 · 이 태스크의 논문 보기 →
Benchmarks
LHQ
결과 1개
Most implemented
Aligning Latent and Image Spaces to Connect the Unconnectable
2021-04-14 · 구현 1개
Papers
DiffCollage: Parallel Generation of Large Content with Diffusion Models
2023-03-30 · CVPR 2023 1
· Qinsheng Zhang, Jiaming Song, Xun Huang, Yongxin Chen 외
We present DiffCollage, a compositional diffusion model that can generate large content by leveraging diffusion models trained on generating pieces of the large content. Our approach is based on a factor graph representa…
Image GenerationInfinite Image GenerationMotion GenerationAligning Latent and Image Spaces to Connect the Unconnectable
2021-04-14 · ICCV 2021 10
· Ivan Skorokhodov, Grigorii Sotnikov, Mohamed Elhoseiny
In this work, we develop a method to generate infinite high-resolution images with diverse and complex content. It is based on a perfectly equivariant generator with synchronous interpolations in the image and latent spa…
DiversityImage GenerationInfinite Image Generation