Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+demo_images/compare_color_fix.png filter=lfs diff=lfs merge=lfs -text
+demo_images/compare_latent_transplant.png filter=lfs diff=lfs merge=lfs -text
+demo_images/input_320x480.jpg filter=lfs diff=lfs merge=lfs -text
+demo_images/upscaled_4x_default.png filter=lfs diff=lfs merge=lfs -text
+demo_images/upscaled_4x_no_color_fix.png filter=lfs diff=lfs merge=lfs -text
+demo_images/upscaled_4x_transplant_off.png filter=lfs diff=lfs merge=lfs -text

.vscode/settings.json

@@ -0,0 +1,4 @@
+{
+    "python-envs.defaultEnvManager": "ms-python.python:conda",
+    "python-envs.defaultPackageManager": "ms-python.python:conda"
+}

README.md

@@ -158,6 +158,30 @@ after 1 pass and +14.8% after 2; the latent mean drift is ~0.1 sigma per pass on
 -0.02, RGB means <= 0.9/255) — every drift mode above is created by the flow
 UNet or by the correction stack itself.
 
+### Visual demo
+
+One-image walkthrough of the two knobs (`demo_images/`): a 320x480 portrait
+upscaled 2 passes (4x) at seed 42.
+
+**Color fix** — both runs at `transplant_strength = 0` so the output
+structure matches the original and only color differs. Uncorrected, the skin
+drifts visibly pale/green (R −3.1, G −0.5, B −2.8 /255 mean cast; mean
+chroma +3.5%); with the fix, means pin to within 0.2/255 and chroma to +0.1%:
+
+![color fix comparison](demo_images/compare_color_fix.png)
+
+**Latent transplant** — both runs at `color_fix_strength = 1`. Strength 1
+nearly doubles measured sharpness (mean abs Laplacian 1.40 -> 2.71) at the
+cost of input fidelity (PSNR to input 43.1 -> 40.8 dB) — the
+fidelity/realism tradeoff, visible in the lashes and iris detail:
+
+![latent transplant comparison](demo_images/compare_latent_transplant.png)
+
+Inputs and full outputs for all three settings are in `demo_images/`. Color
+metrics for this demo were measured through the gradio demo's lossy webp
+output, which inflates the residual percentiles slightly; the tables above
+use the lossless notebook protocol.
+
 ### Nyquist / frequency-band analysis
 
 Band bookkeeping, with frequencies written as fractions of each grid's