Abstract: Embodiments described herein provide a diffusion-based framework that is trained on a dataset with limited text labels, to generate a distribution of data samples in the dataset given a specific text description label. Specifically, firstly, unlabeled data is used to train the diffusion model to generate a data distribution of data samples given a specific text description label. Then text-labeled data samples are used to finetune the diffusion model to generate data distribution given a specific text description label, thus enhancing controllability of training.

Abstract: An application of collagen peptide in the preparation of an allergen preparation auxiliary material. For an allergen preparation, the auxiliary material thereof does not contain biological macromolecules, but contains the collagen peptide, avoiding the risk of potential allergies caused by the introduction of an inactive substance protein. The allergen preparation containing no biological macromolecule auxiliary materials can be stored stably for three years at room temperature. For allergic patients, the allergen preparation is a highly effective, stable and safe drug.