ChatGen: Automatic Text-to-Image Generation From FreeStyle Chatting
Chengyou Jia, Changliang Xia, Zhuohang Dang, Weijia Wu, Hangwei Qian,, Minnan Luo

TL;DR
ChatGen introduces an automated approach to text-to-image generation from freeform chat descriptions, reducing user effort by automating prompt crafting, model selection, and configuration through a new benchmark and multi-stage evolution strategy.
Contribution
The paper presents ChatGen-Evo, a novel multi-stage evolution method for automatic T2I, and introduces ChatGenBench, a comprehensive benchmark for evaluating automatic T2I systems.
Findings
ChatGen-Evo outperforms baseline methods in accuracy and image quality.
The benchmark enables systematic evaluation of automatic T2I steps.
Insights gained can guide future improvements in automatic T2I models.
Abstract
Despite the significant advancements in text-to-image (T2I) generative models, users often face a trial-and-error challenge in practical scenarios. This challenge arises from the complexity and uncertainty of tedious steps such as crafting suitable prompts, selecting appropriate models, and configuring specific arguments, making users resort to labor-intensive attempts for desired images. This paper proposes Automatic T2I generation, which aims to automate these tedious steps, allowing users to simply describe their needs in a freestyle chatting way. To systematically study this problem, we first introduce ChatGenBench, a novel benchmark designed for Automatic T2I. It features high-quality paired data with diverse freestyle inputs, enabling comprehensive evaluation of automatic T2I models across all steps. Additionally, recognizing Automatic T2I as a complex multi-step reasoning task,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMultimodal Machine Learning Applications · Topic Modeling
