AK4Prompts: Aesthetics-driven Automatically Keywords-Ranking for Prompts in Text-To-Image Models

Authors: Haiyang Zhang, Mengchao Wang, Shuai He, Anlong Ming

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experimental results show the superiority of AK4Prompts to improve the quality of generated images significantly over strong baselines.
Researcher Affiliation Academia School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications {zhhy, wangmengchao, hs19951021, mal}@bupt.edu.cn
Pseudocode No The paper includes illustrations and equations in Figure 2 but does not provide structured pseudocode or an algorithm block.
Open Source Code Yes Our code is available at https://github.com/m Robotit/AK4Prompts.
Open Datasets Yes We train our model using Beautiful Prompt s training set and evaluate its performance on the test set. The dataset includes 143k simple prompts and 2k test prompts. We train our model using Beautiful Prompt s training set and evaluate its performance on the test set. [Cao et al., 2023]
Dataset Splits No The paper specifies a training set of 143k and a test set of 2k prompts but does not explicitly mention a distinct validation set or its split details.
Hardware Specification Yes All experiments were implemented in Py Torch and run on a single server with NVIDIA RTX3090TI GPUs.
Software Dependencies No The paper mentions 'implemented in Py Torch' but does not specify a version number for PyTorch or any other software dependencies with their versions.
Experiment Setup Yes We generated 512x512 resolution images through a four-step inference with a CFG scale ω set to 1.0, leveraging FLOAT16 formats to save GPU memory and speed up training. For the semantic fusion module, we set L = 3. Regarding Ltotal, we set h = 2.25, c = 2.25, and a = 1. The learning rate was set at 1e-4, weight decay at 1e-2, batch size at 32, and training step at 88,000 steps.