Card: mark macOS-only (4B over iPhone memory limit); fix app link to zoo apps/CoreAIImageGen

README.md

@@ -24,6 +24,11 @@ FLUX.2 [klein] is step-distilled: **4 denoising steps at guidance 1.0** produce
 1024×1024 image. It pairs a 4B flow-matching diffusion transformer (DiT) with an 8B
 Qwen3 text encoder.
 
+> **macOS only.** At 4B the peak footprint (~6.5 GB — the text encoder stays resident
+> through the transformer) exceeds a 12 GB iPhone's ~6.1 GB per-process memory limit, even
+> with the transformer AOT-compiled. Use a smaller diffusion model (e.g. Stable Diffusion
+> 0.9B) for on-device iOS image generation.
+
 ## Components
 
 | Component | Description |
@@ -42,8 +47,8 @@ VAE 0.16 GB.
 
 ### Sample app (easiest)
 
-[**CoreAIImageGenMac**](https://github.com/mlboydaisuke/coreai-samples) — pick
-"FLUX.2 klein 4B", tap **Download & Load**, type a prompt, **Generate**.
+[**CoreAIImageGen** (macOS)](https://github.com/john-rocky/coreai-model-zoo/tree/main/apps/CoreAIImageGen)
+— run the `CoreAIImageGenMac` scheme, tap **Download & Load**, type a prompt, **Generate**.
 
 ### Swift