# Coyote-A/ultimate-upscale-for-automatic1111

Repository: https://github.com/Coyote-A/ultimate-upscale-for-automatic1111
Canonical: https://ross.abutalabs.com/products/ultimate-upscale-for-automatic1111
Language: Python
License: GPL-3.0
License Family: copyleft
Last push: 2024-06-30T01:06:10+00:00

## Health v2 (maintenance only)
Score: 31/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 95
- inputs: {"age_days": 1339, "days_push": 795, "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 1766, forks 177 (observed 2026-08-28T04:05:33.491400+00:00)

## What it is
An extension for the AUTOMATIC1111 Stable Diffusion web UI that upscales images to 2K/4K+ by processing them in tiled passes with diffusion denoising. It keeps tile sizes small (e.g., 512x512) so it works on low-VRAM GPUs while minimizing seam artifacts.

## Use cases
- upscale stable diffusion images to 4k without artifacts
- enlarge ai-generated art on a low vram gpu
- tile-based img2img upscaling with high denoise
- fix visible seams when upscaling in tiles
- batch upscale images via the automatic1111 api
- upscale anime illustrations with esrgan or swinir

## When to choose
- you already use the AUTOMATIC1111 web UI and want high-resolution outputs
- your GPU cannot fit full-size images so you need tiled processing
- you want denoise during upscaling while suppressing tile seams

## When to avoid
- you use ComfyUI (use the ComfyUI_UltimateSDUpscale port instead)
- you need a standalone upscaler outside the Stable Diffusion web UI
- you only need simple interpolation without diffusion refinement

## Facets
- artifact type: plugin
- maturity: stable
- function: image-processing, stable-diffusion, gpu-computing
- domain: image-processing, artificial-intelligence, web-development
- platform: python, cross-platform
- tags: stable-diffusion-webui, automatic1111-extension, upscaling, tiled-upscale, img2img, gpu

## Member repositories
- Coyote-A/ultimate-upscale-for-automatic1111 (main) score 31

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:33.491400+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 2026-08-30T03:26:28.562736+00:00, confidence not recorded.
  - readme: https://github.com/Coyote-A/ultimate-upscale-for-automatic1111 (fetched 2026-08-28T04:05:33.491400+00:00, sha 02b06a76ed45)
- Data as of 2026-08-30T08:39:29.467469+00:00.