Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

The Chosen One: Consistent Characters in Text-to-Image Diffusion Models

About

Recent advances in text-to-image generation models have unlocked vast potential for visual creativity. However, the users that use these models struggle with the generation of consistent characters, a crucial aspect for numerous real-world applications such as story visualization, game development, asset design, advertising, and more. Current methods typically rely on multiple pre-existing images of the target character or involve labor-intensive manual processes. In this work, we propose a fully automated solution for consistent character generation, with the sole input being a text prompt. We introduce an iterative procedure that, at each stage, identifies a coherent set of images sharing a similar identity and extracts a more consistent identity from this set. Our quantitative analysis demonstrates that our method strikes a better balance between prompt alignment and identity consistency compared to the baseline methods, and these findings are reinforced by a user study. To conclude, we showcase several practical applications of our approach.

Omri Avrahami, Amir Hertz, Yael Vinker, Moab Arar, Shlomi Fruchter, Ohad Fried, Daniel Cohen-Or, Dani Lischinski• 2023

Related benchmarks

TaskDatasetResultRank
Consistent Text-to-Image GenerationConsiStory+ (test)
CLIP-T0.7614
23
Multi-frame visual story generationConsiStory+
CLIP-T76.14
12
Consistent Text-to-Image GenerationConsiStory+ evaluation prompts
Human Preference Rate0.1
8
Showing 3 of 3 rows

Other info

Follow for update