Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.28067 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913166887223296 |
|---|---|
| author | Deng, Fei Xu, Yanwu Bao, Zhipeng Zhang, Zhixing Jia, Haolin Raveendran, Karthik Wei, Jianing |
| author_facet | Deng, Fei Xu, Yanwu Bao, Zhipeng Zhang, Zhixing Jia, Haolin Raveendran, Karthik Wei, Jianing |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_28067 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | BlazeEdit: Generalist Image Editing on Mobile Devices with Image-to-Image Diffusion Models Deng, Fei Xu, Yanwu Bao, Zhipeng Zhang, Zhixing Jia, Haolin Raveendran, Karthik Wei, Jianing Artificial Intelligence 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. |
| title | BlazeEdit: Generalist Image Editing on Mobile Devices with Image-to-Image Diffusion Models |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2605.28067 |