diff --git a/benchmarks/flux2klein/README.md b/benchmarks/flux2klein/README.md index 3ee16c9..deab2ee 100644 --- a/benchmarks/flux2klein/README.md +++ b/benchmarks/flux2klein/README.md @@ -39,6 +39,7 @@ Do not call a workflow fully optimal from one benchmark image. Use these batches ## Latest review +- 2026-08-28 overnight single-image smoke, reviewed: clean full-body studio restage with preserved blonde identity, gold corset, black thigh-high boots, and a clean white seamless background. Keep `runs/2026-08-28T02-07-42-007Z-single-smoke/` as the current benchmark winner for now, but queue one more smoke test before any broader promotion. - 2026-08-27 overnight single-image smoke, reviewed: clean full-body studio restage with preserved blonde identity, gold corset, black thigh-high boots, and a clean white seamless background. Keep `runs/2026-08-27T02-08-31-134Z-single-smoke/` as the current benchmark winner for now, but queue one more smoke test before any broader promotion. - 2026-08-23 overnight single-image smoke: clean full-body white-background restage with strong identity retention, a tidy silhouette, and no obvious background clutter. Keep `runs/2026-08-23T02-05-24-860Z-single-smoke/` as the current benchmark winner, but queue one more smoke test before any broader promotion. - 2026-08-21 overnight single-image smoke: clean full-body studio restage on a pure white background, with good identity retention and a tidy silhouette. Treat it as the current benchmark winner for now, but keep one more smoke test queued before any stronger promotion. diff --git a/benchmarks/flux2klein/overnight-state.json b/benchmarks/flux2klein/overnight-state.json index 6d1ced1..e919b13 100644 --- a/benchmarks/flux2klein/overnight-state.json +++ b/benchmarks/flux2klein/overnight-state.json @@ -24,8 +24,8 @@ } } ], - "reviewPending": true, - "verdict": null, + "reviewPending": false, + "verdict": "Keep the 2026-08-28 single-image smoke as the benchmark winner for now; identity and background stayed clean, but queue one more smoke test before broader promotion.", "date": "2026-08-28T02:09:03.591Z", "optimizedPaths": [ "optimized/image-edit/flux2klein-9b-fp8-edit-master/README.md", diff --git a/optimized/image-edit/flux2klein-9b-fp8-edit-master/README.md b/optimized/image-edit/flux2klein-9b-fp8-edit-master/README.md index 175a4c6..d41f068 100644 --- a/optimized/image-edit/flux2klein-9b-fp8-edit-master/README.md +++ b/optimized/image-edit/flux2klein-9b-fp8-edit-master/README.md @@ -24,7 +24,7 @@ This is built from the official `9B distilled` template because it matches your - Matches your default family: `FLUX.2-klein 9B fp8` - Official Comfy template is a safer foundation than community pages with weak provenance. - Distilled is the most sensible first optimization bias for a `3070`. -- The 2026-08-27 smoke test on this box produced another clean full-body white-background reference, which keeps this as the current practical master. +- The 2026-08-28 smoke test on this box produced another clean full-body white-background reference, which keeps this as the current practical master. ## What I intentionally kept @@ -59,8 +59,9 @@ Fill this out whenever the master is materially updated so we can see exactly wh - LoRAs: none recorded yet - ControlNets / guidance nodes: none recorded yet - Masks / inpaint settings: not recorded yet -- Node-level graph changes: aligned both saved diffusion-model widgets to the real `flux-2-klein-9b-fp8.safetensors` filename and kept the shared `full_encoder_small_decoder.safetensors` VAE; the 2026-08-27 single-image smoke held cleanly at `4` steps, `cfg 1`, `1536x864`, with `euler` and noise seed `26416064315367` +- Node-level graph changes: aligned both saved diffusion-model widgets to the real `flux-2-klein-9b-fp8.safetensors` filename and kept the shared `full_encoder_small_decoder.safetensors` VAE; the 2026-08-28 single-image smoke held cleanly at `4` steps, `cfg 1`, `1536x864`, with `euler` and noise seed `26416064315367` - Smoke test: `2026-08-27`, `4` steps, `cfg 1`, `1536x864`, output `benchmarks/flux2klein/runs/2026-08-27T02-08-31-134Z-single-smoke/cases/case01/01-flux2klein-overnight-smoke_00002_.png` +- Smoke test: `2026-08-28`, `4` steps, `cfg 1`, `1536x864`, output `benchmarks/flux2klein/runs/2026-08-28T02-07-42-007Z-single-smoke/cases/case01/01-flux2klein-overnight-smoke_00003_.png` - Why this change was made: keep the master aligned with your `9B fp8` preference and the actual saved model filenames while staying more practical than the heavier base route ## Required models diff --git a/optimized/notes/flux2klein.md b/optimized/notes/flux2klein.md index 6a6a0c7..efc8cbe 100644 --- a/optimized/notes/flux2klein.md +++ b/optimized/notes/flux2klein.md @@ -49,6 +49,7 @@ - low-step settings when they are clearly validated - better reference/outpaint control if portable - Treat the `geceff` multi-reference pack as a donor for future reference-heavy variants, not as the first default promotion. +- The 2026-08-28 overnight `image-edit-9b-distilled` smoke still looks clean enough to keep `flux2klein-9b-fp8-edit-master` as the benchmark winner for now: identity retention stayed strong, the full-body silhouette remained tidy, and the white background stayed uncluttered. Queue one more smoke test before any broader promotion. - The 2026-08-22 overnight `image-edit-9b-distilled` smoke stayed clean enough to keep the current `flux2klein-9b-fp8-edit-master` lane as the benchmark winner for now: strong identity retention, a tidy full-body silhouette, and a clean white background. Keep one more smoke test queued before any broader claim of stability. - The 2026-08-23 overnight `image-edit-9b-distilled` smoke is still clean enough to keep `flux2klein-9b-fp8-edit-master` as the benchmark winner: identity stayed locked, the body read stayed clean, and the white background remained uncluttered. Queue another smoke test before any stronger promotion. - The 2026-08-27 overnight `image-edit-9b-distilled` smoke held up on review and is still clean enough to keep `flux2klein-9b-fp8-edit-master` as the benchmark winner for now: identity retention is still strong, the silhouette is tidy, and the white background stayed uncluttered. Queue one more smoke test before any broader promotion. diff --git a/optimized/notes/reviews/2026-08-28-daily-review.md b/optimized/notes/reviews/2026-08-28-daily-review.md new file mode 100644 index 0000000..fc22648 --- /dev/null +++ b/optimized/notes/reviews/2026-08-28-daily-review.md @@ -0,0 +1,27 @@ +# 2026-08-28 Daily Review + +## Scope + +Reviewed the overnight `flux2klein` single-image smoke test recorded in `benchmarks/flux2klein/overnight-state.json`. + +## Tests found + +- One successful overnight smoke test in `runs/2026-08-28T02-07-42-007Z-single-smoke/`. +- Workflow: `models/flux2klein/image-edit-9b-distilled/workflow.json` +- Output: `benchmarks/flux2klein/runs/2026-08-28T02-07-42-007Z-single-smoke/cases/case01/01-flux2klein-overnight-smoke_00003_.png` + +## Best output + +- Clean full-body studio restage on a pure white seamless background. +- Identity retention is still strong enough to keep the current winner in place for now. +- The gold corset and black thigh-high boots stayed readable and the silhouette stayed tidy. +- No obvious background clutter or compositional noise. + +## Verdict + +Keep `runs/2026-08-28T02-07-42-007Z-single-smoke/` as the current benchmark winner, but do not treat it as fully settled from one image. + +## Follow-up + +- Queue one more smoke test on a later night. +- Use the next test to confirm the identity lock and background cleanliness hold up across another sample.