MULTI-CONCEPT T2I-ZERO: TWEAKING ONLY THE TEXT EMBEDDINGS AND NOTHING ELSE

The dataset used in the paper is a text-to-image diffusion model, specifically Stable Diffusion. The authors used this model to generate images from text prompts and evaluated its performance on multi-concept image synthesis, image manipulation, and personalization tasks.

Data and Resources

Cite this as

Hazarapet Tunanyan, Dejia Xu, Shant Navasardyan, Zhangyang Wang, Humphrey Shi (2024). Dataset: MULTI-CONCEPT T2I-ZERO: TWEAKING ONLY THE TEXT EMBEDDINGS AND NOTHING ELSE. https://doi.org/10.57702/8jbure2o

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2310.07419
Author Hazarapet Tunanyan
More Authors
Dejia Xu
Shant Navasardyan
Zhangyang Wang
Humphrey Shi
Homepage https://multi-concept-t2i-zero.github.io/