aboutsummaryrefslogtreecommitdiffstats
path: root/AGENTS.md
diff options
context:
space:
mode:
authorDanilo M. <danix@danix.xyz>2026-10-30 18:57:57 +0100
committerDanilo M. <danix@danix.xyz>2026-10-30 18:57:57 +0100
commitb9b19f7ecb9b8549986e2f6bd1fcec3914b68882 (patch)
tree968df6aa254f16802210279793ce5b13b4f21476 /AGENTS.md
parent8553d49a0801d07e21ca9b4113b51181e6c7a72b (diff)
downloadupscale-qt-b9b19f7ecb9b8549986e2f6bd1fcec3914b68882.tar.gz
upscale-qt-b9b19f7ecb9b8549986e2f6bd1fcec3914b68882.zip
Record upscaler test results and imajev prompt rule
Three test images (clean portrait, landscape, noisy phone JPEG) at 4x picked the foolhardy 4x model for clean photos, RealESRGAN_x4plus for degraded ones and the anime model for art. The suggestion prompt must weigh source quality, since imajev chose a detail model for the noisy photo. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Diffstat (limited to 'AGENTS.md')
-rw-r--r--AGENTS.md12
1 files changed, 12 insertions, 0 deletions
diff --git a/AGENTS.md b/AGENTS.md
index d196e48..4f98245 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -22,6 +22,18 @@ Design spec: `docs/superpowers/specs/2026-10-30-upscale-qt-design.md`.
--image <in> -p <prompt>`. Its answer is free text and gets matched to a
filename from the upscalers dir; never trust it as a path.
- Both run through `QProcess` so the UI never blocks.
+- `sd-cli` loads ESRGAN (RRDBNet) and MoSR models only, detected from the
+ weights. SwinIR, HAT, DAT, SPAN, Compact and face restorers do not load.
+- Model choice, measured on 4x crops of a clean portrait, a landscape and a
+ noisy 2009 phone JPEG: the 4x foolhardy model is best on clean photos
+ (people and nature), `RealESRGAN_x4plus` on noisy or compressed sources
+ (smooth, slightly waxy skin), `RealESRGAN_x4plus_anime_6B` for anime and
+ art only. Rejected after testing: 4xNomos2_hq_mosr (amplifies JPEG
+ blocks), 4xNomos8kSC (artifacts on noisy input), 4xLSDIRplusR (plastic
+ on clean input), 4xLSDIRplusC (close to the foolhardy model, not better).
+- Timing: an RRDBNet model takes about 25 s per megapixel of input, so a
+ 10 MP photo takes about 4 minutes and outputs a 160 MP image. imajev
+ answers in about 7 s.
## Conventions