# lquesada/ComfyUI-Inpaint-CropAndStitch

ComfyUI nodes to crop before sampling and stitch back after sampling that speed up inpainting

Repository: https://github.com/lquesada/ComfyUI-Inpaint-CropAndStitch
Canonical: https://ross.abutalabs.com/products/comfyui-inpaint-cropandstitch
Language: Python
License: GPL-3.0
License Family: copyleft
Last push: 2026-08-21T17:02:34+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 35, longevity 60
- inputs: {"age_days": 844, "days_push": 12, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1145, forks 83 (observed 2026-08-28T04:03:45.666142+00:00)

## What it is
A set of ComfyUI custom nodes that crop an image around a masked area before sampling and stitch the inpainted result back afterward. This speeds up inpainting, enables resolution control and upscaling, and leaves unmasked areas untouched.

## Use cases
- speed up inpainting by only sampling the masked area
- outpaint by extending the image beyond its borders
- force a specific sampling resolution like 1024x1024 for SDXL
- upscale a masked region before sampling to add detail
- inpaint without altering unmasked parts of the image
- avoid artifacts like double heads when inpainting large areas

## When to choose
- you use ComfyUI and want faster, higher-quality inpainting or outpainting
- you need precise control over context and resolution during inpainting
- you want unmasked image regions preserved exactly, without VAE round-tripping

## When to avoid
- you don't use ComfyUI or a node-based Stable Diffusion workflow
- you need full-image regeneration rather than masked-region editing

## Facets
- artifact type: plugin
- maturity: active
- function: image-processing, machine-learning, plugin-system
- domain: image-processing, artificial-intelligence, developer-tools
- platform: python, cross-platform
- tags: comfyui, stable-diffusion, inpainting, outpainting, custom-nodes, image-cropping

## Member repositories
- lquesada/ComfyUI-Inpaint-CropAndStitch (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:45.666142+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:34:40.050309+00:00, confidence not recorded.
  - readme: https://github.com/lquesada/ComfyUI-Inpaint-CropAndStitch (fetched 2026-08-28T04:03:45.666142+00:00, sha 5960704e86b5)
- Data as of 2026-08-30T08:39:29.467469+00:00.