SoftPaint: Zero-Shot Soft Masks Enable Pixel-Level Redo with Adjustable Strength in Image and Video Diffusion
HKUST · hf · 2026-10-14
HKUST researchers introduce SoftPaint, a zero-shot sampling method using soft masks to give diffusion-based editing a continuous spectrum of pixel-level control—from fully preserving original content to fully re-synthesizing masked regions. Beyond zero-shot inpainting, they design a Langevin-iteration-based sampler that respects per-pixel soft mask strengths, applying universally to image and video diffusion models and enabling tasks like video editing. The method is gradient-free and memory-efficient, achieving smooth pixel-level edits across multiple image and video backbones.
More from Multimodal
- Customuse launches Smart Mesh AI with geometry-aware adaptive character clothing tool — SimplyAnnisa · 2026-10-23
- AI-generated movie poster 'The Chase' crams a wolf, a plane and muscle cars into one chase — Aggravating-Sir-115 · 2026-10-23
- SteerTTS-edge: an 11.84MB steerable TTS with unchanged WER running 19x realtime on CPU — Working_Hat5120 · 2026-10-23
- ElevenLabs' Chimera pairs Eleven v4 voice with Seedance video to make character images speak — AIwithGhotai · 2026-10-23
- Open-Source Tennis Models Plus Claude Turn Video Into a World-Class Coach — tweetsatpreet · 2026-10-23
- Berkeley's StyleStream 2.0 cuts streaming voice conversion latency to 520ms, 2x faster — Berkeley · 2026-10-23