Emerging text-to-image (T2I) models perpetuate biases, creating stereotypical portrayals of disability. This study investigates whether an agent-based, human-in-loop, AI workflow, that iteratively refines user-provided queries, can produce fairer representations of disability compared to standard models like Stable Diffusion, DALL·E-3, and MidJourney. Sixteen raters (eight with disabilities and eight without) evaluated images generated from models, prompted with textual inputs that targeted professional, medical, or social contexts. In an initial survey, raters were asked if an image depicted a disability, the type of disability if present, and if the setting aligned with the given text prompt to the model. Qualitative comments were collected. A post-survey asked raters to choose which image of a pair (standard vs. agent-based workflow) more accurately represented disability. Results revealed that standard models disproportionately produced images featuring physical disabilities or wheelchairs (p < 0.001), consistent with broader dataset biases. In contrast, the agent-based model’s images were deemed more representative in approximately two-thirds of comparisons (p < 0.0001), especially among raters with disabilities. Qualitative analyses underscored the need for nuanced, contextually rich portrayals.These findings suggest disability bias and that targeted debiasing can help mitigate stereotypes in generative AI, fostering more equitable outputs.