Abstract
Diffusion models with prompt and reference image-guided editing have seen rapid progress, yet they remain too coarse for pixel-level control. One promising direction is to incorporate a soft mask that specifies spatially varying edit strengths but training such fine-grained control demands expensive pixel-wise annotations, while existing zero-shot methods often yield unsatisfactory results. We introduce SoftPaint, a new zero-shot sampling method that leverages soft masks to enable a continuous spectrum of edits, from fully preserving the original content to completely re-synthesizing the masked region. Going beyond zero-shot inpainting methods, we design a Langevin-iteration-based sampler that respects per-pixel soft mask strengths, which applies universally to image and video diffusion models, enabling tasks such as video editing. The method is gradient-free, memory-efficient, and achieves smooth, pixel-level edits across multiple image and video backbones.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Zheng, C., & Lan, Y. (2026). Diffusion Editing with Soft Mask: Pixel Level Redo of Image and Video with Adjustable Strength. https://omanscience.com/en/articles/diffusion-editing-with-soft-mask-pixel-level-redo-of-image-and-video-with-adjustable-strength
MLA 9
Zheng, Candi, and Yuan Lan. "Diffusion Editing with Soft Mask: Pixel Level Redo of Image and Video with Adjustable Strength." https://omanscience.com/en/articles/diffusion-editing-with-soft-mask-pixel-level-redo-of-image-and-video-with-adjustable-strength.
Chicago (author–date)
Zheng, Candi, and Yuan Lan. 2026. "Diffusion Editing with Soft Mask: Pixel Level Redo of Image and Video with Adjustable Strength." https://omanscience.com/en/articles/diffusion-editing-with-soft-mask-pixel-level-redo-of-image-and-video-with-adjustable-strength.
Harvard
Zheng, C. and Lan, Y. (2026) 'Diffusion Editing with Soft Mask: Pixel Level Redo of Image and Video with Adjustable Strength', Available at: https://omanscience.com/en/articles/diffusion-editing-with-soft-mask-pixel-level-redo-of-image-and-video-with-adjustable-strength.
Vancouver
Zheng C, Lan Y. Diffusion Editing with Soft Mask: Pixel Level Redo of Image and Video with Adjustable Strength. https://omanscience.com/en/articles/diffusion-editing-with-soft-mask-pixel-level-redo-of-image-and-video-with-adjustable-strength
IEEE
C. Zheng, and Y. Lan, "Diffusion Editing with Soft Mask: Pixel Level Redo of Image and Video with Adjustable Strength," https://omanscience.com/en/articles/diffusion-editing-with-soft-mask-pixel-level-redo-of-image-and-video-with-adjustable-strength.