From a2f9e007ac5fb98b473ca2bbf662fc4354338a28 Mon Sep 17 00:00:00 2001
From: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Wed, 8 Oct 2025 16:01:38 +1100
Subject: [PATCH] feat(mm): fix clip vision starter model bases, add ref to
 actual models

---
 invokeai/backend/model_manager/starter_models.py | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/invokeai/backend/model_manager/starter_models.py b/invokeai/backend/model_manager/starter_models.py
index 84e98fed4d..8958b6fd3c 100644
--- a/invokeai/backend/model_manager/starter_models.py
+++ b/invokeai/backend/model_manager/starter_models.py
@@ -37,16 +37,20 @@ cyberrealistic_negative = StarterModel(
 )
 
 # region CLIP Image Encoders
+
+# This is CLIP-ViT-H-14-laion2B-s32B-b79K
 ip_adapter_sd_image_encoder = StarterModel(
     name="IP Adapter SD1.5 Image Encoder",
-    base=BaseModelType.StableDiffusion1,
+    base=BaseModelType.Any,
     source="InvokeAI/ip_adapter_sd_image_encoder",
     description="IP Adapter SD Image Encoder",
     type=ModelType.CLIPVision,
 )
+
+# This is CLIP-ViT-bigG-14-laion2B-39B-b160k
 ip_adapter_sdxl_image_encoder = StarterModel(
     name="IP Adapter SDXL Image Encoder",
-    base=BaseModelType.StableDiffusionXL,
+    base=BaseModelType.Any,
     source="InvokeAI/ip_adapter_sdxl_image_encoder",
     description="IP Adapter SDXL Image Encoder",
     type=ModelType.CLIPVision,