scraed/LanPaint
High quality training free inpaint for every stable diffusion model. Supports ComfyUI
What it solves
LanPaint 提供一個通用、無需訓練的修補與延伸解決方案，適用於擴散模型。它消除了對模型特定修補訓練或複雜混合技巧的需求，讓使用者能夠在圖像與影片的遮罩區域內，使用現有模型產生高品質、無縫的新內容。
How it works
LanPaint 引入一個專門的抽樣器，實作「思考模式」。此模式允許模型在最終去噪過程之前，執行多次「思考」迭代。透過這些迭代投入更多計算時間，抽樣器可達到漸近精確且快速的條件抽樣，從而在不需重新訓練模型的情況下，提升修補品質。
Who it’s for
此工具主要設計給使用 ComfyUI 的 AI 藝術家與開發者，讓他們能在各種模型（如 Flux、SDXL、Wan 2.2 等）上執行高保真度的修補與延伸，而不必自行訓練專屬的修補模型。
Highlights
- Universal Compatibility: Works with a vast array of models including Ideogram4, Krea2, Z-image, Hunyuan, Wan 2.2, Qwen, Anima, SD 3.5, Flux, and SDXL.
- Training-Free: Operates out of the box with existing models without any additional training.
- Video Support: Capable of video inpainting and outpainting (specifically with Wan 2.2) while maintaining temporal consistency.
- Think Mode: A unique sampling approach that lets users trade computation time for higher quality results.
- Flexible Masking: Supports any mask shape, size, or position for both inpainting and outpainting.