From deaeb6427fc5c8872029de67ceb8260a4614b7b0 Mon Sep 17 00:00:00 2001 From: Morpheus Date: Sun, 27 Sep 2026 08:59:13 +0000 Subject: [PATCH] Record Qwen anatomy review --- optimized/T2I/qwen/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/optimized/T2I/qwen/README.md b/optimized/T2I/qwen/README.md index 33f83c6..3352791 100644 --- a/optimized/T2I/qwen/README.md +++ b/optimized/T2I/qwen/README.md @@ -121,7 +121,7 @@ Files: Visual evaluation notes: - Full matrix status: 88/88 tested; 35/35 newly collected in this batch. - Current best remains Q-T2I-49: `euler_cfg_pp`, beta, 25 steps, CFG 2.5, 110.6s. -- Strong new alternatives, but not promoted: Q-T2I-54–57, Q-T2I-61–64, and Q-T2I-82–84. The normal-scheduler Euler family was the strongest new group, but did not clearly exceed Q-T2I-49 in subject detail, composition, and overall prompt adherence. +- Strong new alternatives, but not promoted: Q-T2I-54–57 and Q-T2I-61–64. Q-T2I-82 and Q-T2I-84 initially appeared strong technically, but were rejected after review for visibly deformed legs/feet. - Valid but weaker: Q-T2I-85. -- Rejected for severe corruption or unusable exposure: Q-T2I-58–60, Q-T2I-65–81, and Q-T2I-86–88. +- Rejected for anatomy, severe corruption, or unusable exposure: Q-T2I-82, Q-T2I-84, Q-T2I-58–60, Q-T2I-65–81, and Q-T2I-86–88. - Earlier rejected rows remain: Q-T2I-17, Q-T2I-18, Q-T2I-19, Q-T2I-22, Q-T2I-23, Q-T2I-46, Q-T2I-47, Q-T2I-48, Q-T2I-51, and Q-T2I-52.