SOTAVerified

Story Continuation

The task involves providing an initial scene that can be obtained in real world use cases. By including this scene, a model can then copy and adapt elements from it as it generates subsequent images.

Source: StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 10 papers

TitleStatusHype
Synthesizing Coherent Story with Auto-Regressive Latent Diffusion ModelsCode2
StoryBench: A Multifaceted Benchmark for Continuous Story VisualizationCode1
Forms of Anaphoric Reference to Organisational Named Entities: Hoping to widen appeal, they diversified—0
Telling Stories through Multi-User Dialogue by Modeling Character Relations—0
Event versus entity co-reference: Effects of context and form of referring expression—0
Quality Signals in Generated Stories—0
ContextualStory: Consistent Visual Storytelling with Spatially-Enhanced and Storyline ContextCode0
How Far Can We Extract Diverse Perspectives from Large Language Models?Code0
StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story ContinuationCode0
Conveying the Predicted Future to Users: A Case Study of Story Plot PredictionCode0
Show:102550
All datasetsFlintstonesSVPororoSVVIST

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1StoryDALL-E (Story Embeddings + Cross-Attention)FID36.28—Unverified
2StoryDALL-E (Cross-Attention)FID35.04—Unverified
3StoryDALL-E (Story Embeddings)FID29.21—Unverified
4StoryDALL-EFID28.37—Unverified
5AR-LDMFID19.28—Unverified
6ContextualStoryFID16.33—Unverified
#ModelMetricClaimedVerifiedStatus
1StoryDALL-E (Story Embeddings + Cross-Attention)FID31.68—Unverified
2StoryDALL-E (Story Embeddings)FID30.45—Unverified
3StoryDALL-E (Cross-Attention)FID23.27—Unverified
4StoryDALL-EFID21.64—Unverified
5AR-LDMFID17.4—Unverified
6ContextualStoryFID14.2—Unverified
#ModelMetricClaimedVerifiedStatus
1AR-LDM (DII captions)FID17.03—Unverified
2AR-LDM (SIS captions)FID16.95—Unverified