diff --git a/README.md b/README.md
index bd42cba..1c46812 100644
--- a/README.md
+++ b/README.md
@@ -112,6 +112,13 @@ partially.
 
 ## Tips
 
+- **The reference's colors ARE the character's identity.** To restyle an
+  attribute, change it in the reference, not the prompt: a grayscale copy of
+  the character ref + "the entire image is black and white" produces a fully
+  monochrome scene (`examples/girl_in_rubberhose_bw.png`); with the color
+  ref, the character keeps her palette no matter what the prompt says.
+  Raising `strength_dit` does NOT help here — it pulls toward the LoRA's
+  (colorful) training distribution.
 - CFG 1.0 on Turbo skips the negative prompt entirely — it's not a bug.
 - Wide canvases encourage figure duplication; 1024×1024 is the sweet spot.
 - For exact pose: pose image as init latent, denoise 0.70–0.78.
diff --git a/examples/girl_in_rubberhose_bw.png b/examples/girl_in_rubberhose_bw.png
new file mode 100644
index 0000000..ffef882
Binary files /dev/null and b/examples/girl_in_rubberhose_bw.png differ