3 papers
cs.CV2024
EVALALIGN: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models
Zhiyu Tan, Xiaomeng Yang, Luozheng Qin +3
The recent advancements in text-to-image generative models have been remarkable. Yet, the field suffers from a lack of evaluation metrics that accurately reflect the performance of…
cs.CV2024
An Empirical Study and Analysis of Text-to-Image Generation Using Large Language Model-Powered Textual Representation
Zhiyu Tan, Mengping Yang, Luozheng Qin +5
One critical prerequisite for faithful text-to-image generation is the accurate understanding of text inputs. Existing methods leverage the text encoder of the CLIP model to repres…
cs.CV2024
Towards Effective Usage of Human-Centric Priors in Diffusion Models for Text-based Human Image Generation
Junyan Wang, Zhenhong Sun, Zhiyu Tan +5
Vanilla text-to-image diffusion models struggle with generating accurate human images, commonly resulting in imperfect anatomies such as unnatural postures or disproportionate limb…