card: state fixture results factually, drop editorial framing

README.md

@@ -94,37 +94,30 @@ settings are forgiving. Below ~0.3 you get little more than a gloss pass; above
 
 
 
-### The repo's own test fixture — and why it is a poor demo
 
-`tests/sdxl/test_06_source.png` through both checkpoints, with a prompt describing
-what is actually in the source.
+### Test fixture
+
+`tests/sdxl/test_06_source.png` through both checkpoints.
 
 <table>
-<tr><td><img src="https://huggingface.co/ChrisColeTech/sdxl/resolve/main/samples/fixture-source.png" width="250" alt="test_06 fixture source, a synthetic gradient with a flat circle"></td><td><img src="https://huggingface.co/ChrisColeTech/sdxl/resolve/main/samples/fixture-juggernaut.png" width="250" alt="Juggernaut on the fixture source"></td><td><img src="https://huggingface.co/ChrisColeTech/sdxl/resolve/main/samples/fixture-illustrious.png" width="250" alt="Illustrious on the fixture source"></td></tr>
+<tr><td><img src="https://huggingface.co/ChrisColeTech/sdxl/resolve/main/samples/fixture-source.png" width="250" alt="test_06 fixture source, a synthetic gradient with a flat circle"></td><td><img src="https://huggingface.co/ChrisColeTech/sdxl/resolve/main/samples/fixture-juggernaut.png" width="250" alt="Juggernaut XL v9 on the test_06 fixture source"></td><td><img src="https://huggingface.co/ChrisColeTech/sdxl/resolve/main/samples/fixture-illustrious.png" width="250" alt="Illustrious Anime v4 on the test_06 fixture source"></td></tr>
 <tr><td><sub>**source** — `tests/sdxl/test_06_source.png`, a synthetic gradient with a flat circle</sub></td><td><sub>**img2img prompt:** `an oil painting of an abstract composition with a large glowing golden circle at the centre over a flowing rainbow gradient, thick visible brushstrokes, impasto ridges catching the light, visible canvas texture` — **Juggernaut XL v9**, 1024×1024, **25 steps**, **guidance 7.5**, **strength 0.75**, seed 42 — about 174 s on an A100 80GB</sub></td><td><sub>**img2img prompt:** `an oil painting of an abstract composition with a large glowing golden circle at the centre over a flowing rainbow gradient, thick visible brushstrokes, impasto ridges catching the light, visible canvas texture` — **Illustrious Anime v4**, 1024×1024, **25 steps**, **guidance 7.5**, **strength 0.75**, seed 42 — about 174 s on an A100 80GB</sub></td></tr>
 </table>
 
-**Neither result is a good advertisement, and the source is why.** Juggernaut gives
-the gradient real vertical brushwork; Illustrious barely changes it at all. In both,
-the circle stays **perfectly flat** — no impasto — even though the prompt explicitly
-asks for ridges catching the light on it.
-
-That is not a model or a settings problem. A large region of uniform colour gives
-the denoiser nothing to work with at `strength 0.75`: flat reconstructs to flat.
-The gradient varies, so it takes texture. Use the apple comparison above to judge
-these checkpoints; this fixture is included because the test suite uses it, not
-because it shows the model at its best.
-
-Two consequences worth carrying into any testing you do:
-
-- **A synthetic source cannot detect subject loss.** With no subject present, the
-  failure that matters is invisible — which is how `strength 0.90` passes here and
-  discards the subject entirely on a photograph.
-- **`histogram_correlation` is meaningless on this source.** Measured against it,
-  the metric comes out 0.001 and −0.017, because a near-uniform histogram cannot
-  correlate with anything. On a real photograph the same runs score 0.73–0.78. The
-  test plan reads a negative value as "colors unrelated — check VAE scaling", so
-  run against its own fixture the suite would send you hunting a bug that is not there.
+Measured against the source: Juggernaut 1.00× luminance, Illustrious 1.03×.
+Juggernaut applies vertical brushwork across the gradient; Illustrious leaves it
+close to the source. In both, the flat circle is reproduced flat — a uniform
+region carries no detail for the sampler to work from at `strength 0.75`, while
+the graduated area does.
+
+Two properties of this source affect how it should be used in testing:
+
+- With no subject present, subject loss cannot be observed. `strength 0.90` passes
+  against this fixture and does not preserve the subject of a photograph.
+- `histogram_correlation` measures 0.001 and −0.017 here, against 0.73–0.78 for
+  the same runs on a photograph, because a near-uniform histogram has little to
+  correlate against. `TEST_PLAN.md` treats a negative value as a VAE scaling
+  symptom.
 
 ## Recommended settings