Due to the ambiguity of text and the lack of location information in training data, current state-of-the-art diffusion model cannot accurately control the locations of generated objects in the image under the condition of text prompts. To address this issue, a spatial condition of the object’s location range was introduced, and an attention-guided method was proposed based on the strong correlation between the cross-attention map in U-Net and the image spatial layout to control the generation of the attention map, thus controlling the locations of the generated objects. Specifically, based on the Stable Diffusion (SD) model, in the early stage of the generation of the cross-attention map in the U-Net layer, a loss was introduced to stimulate high attention values in the corresponding location range, and reduce the average attention value outside the range. The noise vector in the latent space was optimized step by step in each denoising step to control the generation of the attention map. Experimental results show that the proposed method can significantly control the locations of one or more objects in the generated image, and when generating multiple objects, it can reduce the phenomenon of object omission, redundant object generation, and object fusion.
In order to support the distributed transmission of a lot of tasks on the data exchange platform for civil aviation information, it needs to establish the efficient task scheduling algorithms and models. Based on the infrastructure and needs of the platform, after analyzing the existing task scheduling models and scheduling algorithms, a new task scheduling model was proposed to fulfill the data exchange on this platform. This model mapped the point-to-multipoint data transmission network to a Steiner tree problem with delay and bandwidth constraints, and an improved Genetic Algorithm (GA) was also proposed to solve the constrained Steiner tree problem. The results of comparative experiment with the maximum bandwidth allocation algorithm prove the validity and feasibility of the proposed model.