---
title: "LanPaint on Comfy Cloud"
description: "LanPaint is preinstalled on Comfy Cloud — 11 nodes ready to run on managed GPUs. Achieve seamless inpainting results without needing a specialized inpainting model."
canonical: https://comfy.org/cloud/supported-nodes/LanPaint/
lang: en
index: https://comfy.org/llms.txt
---

[Back to all packs](https://comfy.org/cloud/supported-nodes/)

# LanPaint

Achieve seamless inpainting results without needing a specialized inpainting model.

**View repository**

[https://github.com/scraed/LanPaint](https://github.com/scraed/LanPaint)

**Publisher**

scraed

**Downloads**

230,038

**GitHub stars**

1,480

**Latest version**

2.1.0

**License**

GNU General Public License v3

**Last updated**

Aug 12, 2026

## Nodes in this pack

### audio

- LanPaint MiniMax Audio Decode

  Decode a MiniMax H3 audio latent to a waveform.
- LanPaint MiniMax Audio Encode

  Encode audio with the MiniMax H3 audio VAE (correct layout). Audio inpainting masks come from the video mask editor via SetLatentNoiseMask.

### image

- LanPaint Image Decode

  Decode an inpainted latent, resize to the original image's exact dimensions, and merge with the original inside the mask (replaces VAEDecode + MaskBlend).
- LanPaint Image Encode

  Encode an image and attach an inpainting mask to the latent (replaces VAEEncode + SetLatentNoiseMask).

### image/postprocessing

- LanPaint Mask Blend

### sampling

- LanPaint KSampler

  Uses the provided model, positive and negative conditioning to denoise the latent image.
- LanPaint KSampler (Advanced)

### sampling/custom_sampling

- LanPaint Sampler Custom
- LanPaint Sampler Custom (Advanced)

### video

- LanPaint AV Decode

  Decode the nested AV latent, merge the inpainted video and audio with the original (mask-blended), and write the result with the original fps and bit depth.
- LanPaint AV Encode

  Encode a video's frames and audio into a nested AV latent with per-stream video and audio masks (1 = regenerate, 0 = keep).