Subject-driven Text-to-Image Generation via Preference-based Reinforcement Learning

doi:doi:10.57702/b1svg0nj

Subject-driven Text-to-Image Generation via Preference-based Reinforcement Learning

Text-to-image generative models have recently attracted considerable interest, enabling the synthesis of high-quality images from textual prompts. However, these models often lack the capability to generate specific subjects from given reference images or to synthesize novel renditions under varying conditions.

BibTex:

@dataset{Yanting_Miao_and_William_Loh_and_Suraj_Kothawade_and_Pascal_Poupart_and_Abdullah_Rashwan_and_Yeqing_Li_2024,
    abstract = {Text-to-image generative models have recently attracted considerable interest, enabling the synthesis of high-quality images from textual prompts. However, these models often lack the capability to generate specific subjects from given reference images or to synthesize novel renditions under varying conditions.},
    author = {Yanting Miao and William Loh and Suraj Kothawade and Pascal Poupart and Abdullah Rashwan and Yeqing Li},
    doi = {10.57702/b1svg0nj},
    institution = {No Organization},
    keyword = {'Preference-based Reinforcement Learning', 'Subject-driven Generation', 'Text-to-Image Generation'},
    month = {dec},
    publisher = {TIB},
    title = {Subject-driven Text-to-Image Generation via Preference-based Reinforcement Learning},
    url = {https://service.tib.eu/ldmservice/dataset/subject-driven-text-to-image-generation-via-preference-based-reinforcement-learning},
    year = {2024}
}