diff --git a/data/reference-community.json b/data/reference-community.json
index e107d10f1..6af580180 100644
--- a/data/reference-community.json
+++ b/data/reference-community.json
@@ -132,20 +132,12 @@
     "date": "2025 January",
     "skip": true
   },
-  "Anima Preview 1": {
-    "path": "CalamitousFelicitousness/Anima-sdnext-diffusers",
-    "preview": "CalamitousFelicitousness--Anima-sdnext-diffusers.jpg",
-    "desc": "Modified Cosmos-Predict-2B that replaces the T5-11B text encoder with Qwen3-0.6B. Anima is a 2 billion parameter text-to-image model created via a collaboration between CircleStone Labs and Comfy Org. It is focused mainly on anime concepts, characters, and styles, but is also capable of generating a wide variety of other non-photorealistic content. The model is designed for making illustrations and artistic images, and will not work well at realism.",
+  "Anima Preview 3": {
+    "path": "CalamitousFelicitousness/Anima-Preview-3-sdnext-diffusers",
+    "preview": "CalamitousFelicitousness--Anima-Preview-3-sdnext-diffusers.jpg",
+    "desc": "Anima Preview V3 with extended 1024-resolution training and expanded dataset coverage for less common artists. A 2B parameter anime-focused text-to-image model based on modified Cosmos-Predict-2B with Qwen3-0.6B text encoder, created by CircleStone Labs and Comfy Org.",
     "tags": "community",
-    "date": "2026 January",
-    "skip": true
-  },
-  "Anima Preview 2": {
-    "path": "CalamitousFelicitousness/Anima-Preview-2-sdnext-diffusers",
-    "preview": "CalamitousFelicitousness--Anima-Preview-2-sdnext-diffusers.jpg",
-    "desc": "Anima Preview V2 with improved hyperparameters, extended medium-resolution training for more character knowledge, and a regularization dataset for better natural language comprehension. A 2B parameter anime-focused text-to-image model based on modified Cosmos-Predict-2B with Qwen3-0.6B text encoder.",
-    "tags": "community",
-    "date": "2026 March",
+    "date": "2026 April",
     "skip": true
   },
   "FireRed Image Edit 1.0": {
diff --git a/models/Reference/CalamitousFelicitousness--Anima-Preview-3-sdnext-diffusers.jpg b/models/Reference/CalamitousFelicitousness--Anima-Preview-3-sdnext-diffusers.jpg
new file mode 100644
index 000000000..2cb08ca5b
Binary files /dev/null and b/models/Reference/CalamitousFelicitousness--Anima-Preview-3-sdnext-diffusers.jpg differ
diff --git a/test/test-detailer-api.py b/test/test-detailer-api.py
index acc4622d7..09adbb67b 100644
--- a/test/test-detailer-api.py
+++ b/test/test-detailer-api.py
@@ -30,7 +30,7 @@ FACE_TEST_IMAGES = [
     'models/Reference/ponyRealism_V23.jpg',                               # realistic woman, clear face
     'models/Reference/HiDream-ai--HiDream-I1-Fast.jpg',                   # realistic man, clear face + text
     'models/Reference/stabilityai--stable-diffusion-xl-base-1.0.jpg',     # realistic woman portrait
-    'models/Reference/CalamitousFelicitousness--Anima-sdnext-diffusers.jpg',  # anime face (non-realistic test)
+    'models/Reference/CalamitousFelicitousness--Anima-Preview-3-sdnext-diffusers.jpg',  # anime face (non-realistic test)
 ]
 
 # Fallback images (no guaranteed faces)