AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

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

Adyasha Maharana, Darryl Hannan, Mohit Bansal

ECCV 2022 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 84 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add cross-attention layers over the source frame (ablation)StoryDALL-E (finetuning) · DiDeMoSV valFID: 55.89 -> 41.58Improved
add cross-attention layers over the source frame (ablation)StoryDALL-E (finetuning) · PororoSV valFID: 30.45 -> 21.64Improved
add cross-attention layers over the source frame (ablation)StoryDALL-E (finetuning) · FlintstonesSV valFID: 35.04 -> 28.37Improved
add global story embeddings (ablation)StoryDALL-E (finetuning) · PororoSV valFID: 23.27 -> 21.64Improved
add global story embeddings (ablation)StoryDALL-E (finetuning) · DiDeMoSV valFID: 42.34 -> 41.58Improved
add both cross-attention and story embeddings (vs text-to-image only) (ablation)StoryDALL-E (finetuning) · DiDeMoSV valFID: 58.14 -> 41.58Improved
full finetuning instead of prompt-tuningStoryDALL-E · PororoSV testFID: 61.23 -> 25.90Improved
full finetuning instead of prompt-tuningStoryDALL-E · PororoSV testcharacter F1: 29.68 -> 36.97Improved
use pretrained StoryDALL-E (finetuned) instead of StoryGAN (BERT)StoryDALL-E · DiDeMoSV testFID: 91.43 -> 32.92Improved
use pretrained StoryDALL-E (finetuned) instead of StoryGAN (BERT)StoryDALL-E · PororoSV testcharacter F1: 43.22 -> 36.97Hurt
use DALL-E Mega instead of minDALL-EStoryDALL-E · PororoSV testFID: 25.90 -> 23.48Improved
StoryDALL-E finetuning vs StoryGAN (BERT) in human evaluation of relevanceStoryDALL-E · FlintstonesSV human evaluation (relevance)win/lose/tie %: 32/38/30Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy