Story Continuation On Flintstonessv
평가 지표
FID
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | FID | Paper Title | Repository |
|---|---|---|---|
| AR-LDM | 19.28 | Synthesizing Coherent Story with Auto-Regressive Latent Diffusion Models | |
| StoryDALL-E (Cross-Attention) | 35.04 | StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation | |
| StoryDALL-E (Story Embeddings) | 29.21 | StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation | |
| ContextualStory | 16.33 | ContextualStory: Consistent Visual Storytelling with Spatially-Enhanced and Storyline Context | |
| StoryDALL-E (Story Embeddings + Cross-Attention) | 36.28 | StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation | |
| StoryDALL-E | 28.37 | StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation |
0 of 6 row(s) selected.