195M参数模型实现手机端快速图像编辑，无需云端
BlazeEdit: Generalist Image Editing on Mobile Devices with Image-to-Image Diffusion Models
- 去除文本条件，用多任务架构整合多种编辑功能
- 在Pixel 10上仅需290ms完成一次推理
- 适合注重隐私与速度的移动端通用图像编辑
现代扩散模型生成质量虽高，但参数量巨大，通常需依赖服务器端推理，带来高昂计算成本和隐私风险。为此，研究者正致力于开发高效的移动端替代方案。尽管近期已有针对移动设备优化的文生图模型，但其参数量仍达0.5B至1B，体积较大。本文提出BlazeEdit，一个专为移动端部署设计的高效通用图像到图像扩散模型。通过发现多数实际图像编辑任务无需文本引导，我们移除了文本条件模块，并构建了一个融合物体移除、外绘、色调校正、光照重制及贴纸生成的多任务架构，模型仅含195M参数。该模型显著降低下载大小与内存开销，同时保持竞争力的生成质量。在Pixel 10上，单次推理仅耗时290ms，实现无缝、私密且极速的边缘端通用图像编辑体验。
原文摘要 · Abstract (English)
The remarkable generation quality of modern diffusion models often comes at the cost of massive parameter counts, which necessitate server-side inference with significant computational costs and potential privacy risks. Consequently, there is growing momentum toward developing efficient on-device alternatives. While recent efforts have optimized text-to-image models for mobile hardware, they remain relatively bulky, typically ranging from 0.5B to 1B parameters. We present BlazeEdit, a highly efficient, generalist image-to-image diffusion model tailored for on-device deployment. By identifying that many practical image editing tasks do not require text-based guidance, we eliminate the text-conditioning components and develop a multi-task architecture that consolidates object removal, outpainting, tone correction, relighting, and sticker generation into a single, compact model of only 195M parameters. BlazeEdit achieves a substantial reduction in download size and memory overhead while maintaining competitive generation quality. It completes a full inference pass in just 290ms on a Pixel 10, delivering a seamless, privacy-preserving, and lightning-fast experience for generalist image editing on the edge.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。