Add depth and multimodal generation capabilities

config.schema.json

@@ -49,12 +49,15 @@
           "semantic-segmentation",
           "instance-segmentation",
           "style-transfer",
+          "depth-estimation",
           "text-embedding",
           "image-embedding",
           "image-generation",
           "voice-activity-detection",
           "text-detection",
-          "text-recognition"
+          "text-recognition",
+          "image-text-to-text",
+          "audio-text-to-text"
         ]
       }
     },