DiffusionX: Efficient Edge-Cloud Collaborative Image Generation with Multi-Round Prompt Evolution
This work addresses efficiency and resource burden for users and cloud providers in image generation, representing an incremental improvement over existing methods.
The paper tackles the computational intensity and latency of iterative prompt refinement in diffusion-based image generation by proposing DiffusionX, a cloud-edge collaborative framework that reduces average generation time by 15.8% compared to Stable Diffusion v1.5 while maintaining comparable image quality.
Recent advances in diffusion models have driven remarkable progress in image generation. However, the generation process remains computationally intensive, and users often need to iteratively refine prompts to achieve the desired results, further increasing latency and placing a heavy burden on cloud resources. To address this challenge, we propose DiffusionX, a cloud-edge collaborative framework for efficient multi-round, prompt-based generation. In this system, a lightweight on-device diffusion model interacts with users by rapidly producing preview images, while a high-capacity cloud model performs final refinements after the prompt is finalized. We further introduce a noise level predictor that dynamically balances the computation load, optimizing the trade-off between latency and cloud workload. Experiments show that DiffusionX reduces average generation time by 15.8% compared with Stable Diffusion v1.5, while maintaining comparable image quality. Moreover, it is only 0.9% slower than Tiny-SD with significantly improved image quality, thereby demonstrating efficiency and scalability with minimal overhead.