Credit reference image galleries and armV5 continuation

README.md

@@ -61,6 +61,17 @@ not part of this recipe. Automatic framing aligns face position/scale/roll and
 may suppress headwear or locally correct unequal eye geometry. It uses a verified
 MediaPipe landmark model stored in `models/mediapipe`.
 
+## Image sources and credits
+
+Face reference images come from the [AI Portrait Gallery](https://ai-portrait-gallery.pages.dev/)
+by [あぎ](https://x.com/agi_aibusi). Costume reference images come from the
+[AI Costume Gallery](https://ai-costume-gallery.pages.dev/).
+These galleries supplied the face/outfit references used to build the training
+examples and preview libraries. The four-panel images displayed in this release
+were generated with the supplied character-card workflow. Original gallery images
+retain their source terms and are not bundled in this model release.
+Thanks to the original gallery creators.
+
 ## Release examples
 
 These are original generated adult anatomy/design studies with privacy coverage
@@ -77,7 +88,7 @@ are shortened in the edited recording; the generated results are unchanged.
 
 ## Training and provenance
 
-Initialized from [akhaliq/MOSS-Image-Edit-HQ armV5](https://huggingface.co/akhaliq/MOSS-Image-Edit-HQ/tree/ee1493ba577437e70b88bc4499b85cc7aa4594ca/weights/armV5),
+This LoRA was further fine-tuned from [akhaliq/MOSS-Image-Edit-HQ armV5](https://huggingface.co/akhaliq/MOSS-Image-Edit-HQ/tree/ee1493ba577437e70b88bc4499b85cc7aa4594ca/weights/armV5),
 on the original [OpenMOSS-Team/MOSS-Image-SFT](https://huggingface.co/OpenMOSS-Team/MOSS-Image-SFT).
 The continuation used 11 synthetic identities, 22 approved target cards with
 paired coverage On/Off, and three input-reference variants: 66 reference/target