Minority-Focused Text-to-Image Generation via Prompt Optimization

Figure 1 . Example results from our minority generation approach using SDXL-Lightning. Our framework is designed to produce unique minority samples w.r.t. user-provided prompts, which are rarely generated by standard samplers like DDIM [46] . Due to its low-likelihood encouraging nature, our sampler often demonstrates counteracting results against demographic biases in text-to-image models [13] . See the samples in the last row for instance, where our sampler mitigates prevalent age and racial biases (e.g., associating "man" with "young" and "woman" with "white") by modifying the demographic traits of the subjects.