Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ 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
+fig_guidance_scale.png filter=lfs diff=lfs merge=lfs -text
+fig_qualitative_comparison.png filter=lfs diff=lfs merge=lfs -text
+fig_training_dynamics.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -36,6 +36,24 @@ This model adapts Stable Diffusion 1.5 for longitudinal retinal image prediction
 
 Evaluated on 110 held-out test image pairs.
 
+## Qualitative Results
+
+![Qualitative comparison](fig_qualitative_comparison.png)
+
+Each row shows a different test patient. Columns: baseline fundus, ground-truth follow-up, our prediction, Regression U-Net, and Pix2Pix. Our diffusion model generates sharper, more realistic retinal textures compared to deterministic baselines.
+
+## Training Dynamics
+
+![Training dynamics](fig_training_dynamics.png)
+
+(a, b) Stage 1: VAE fine-tuning over 50 epochs reaching SSIM 0.954. (c-f) Stage 2: U-Net training over 500 epochs with cosine LR schedule and warmup.
+
+## Guidance Scale Sweep
+
+![Guidance scale](fig_guidance_scale.png)
+
+SSIM peaks at guidance scale 7.5, while FID increases monotonically with stronger guidance, reflecting the fidelity-diversity tradeoff.
+
 ## Usage
 
 ```python