From 6c5409113076b7f153b855a7f3ced341f54aa247 Mon Sep 17 00:00:00 2001 From: MODELBEAST Date: Sun, 12 Jul 2026 23:27:37 +1000 Subject: [PATCH] BENCHMARKS: first local-vs-cloud image A/B (Klein 4B vs nano-banana) Co-Authored-By: Claude Fable 5 --- BENCHMARKS.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/BENCHMARKS.md b/BENCHMARKS.md index 72e7572..b83bc41 100644 --- a/BENCHMARKS.md +++ b/BENCHMARKS.md @@ -20,6 +20,8 @@ and a much crisper splat than the 1500-step preview above. Warm-model runs are the ~8s figure; each new model variant pays its download once. +**First A/B (same prompt, 2026-07-12):** FLUX.2 Klein 4B local (8s, $0) vs nano-banana via OpenRouter (`google/gemini-2.5-flash-image`, 7.7s, $0.0387 exact-billed). Klein: cleaner product-photo subject. nano-banana: richer scene dressing (books/inkwell/quill, dust motes) + finer engraving detail. Verdict: Klein is the volume workhorse; nano-banana wins on scene storytelling per prompt-adherence expectations (Elo 1154 vs ~1083). + ## Mesh-gen (installed; first real run blocked on owner HuggingFace auth) | Operator | Install | Runtime status | |---|---|---|