Implement BiRefNet and HAT Sharper models with background removal capabilities

- Added validation documentation for AI model tiers.
- Introduced `background.py` for background removal logic, including inference functions for alpha and foreground extraction.
- Created `onnx_birefnet.py` to handle BiRefNet model sessions and alpha inference.
- Developed tests for background models, ensuring proper dispatch and session reuse.
- Added tests for BiRefNet ONNX model to validate alpha output and error handling for invalid values.
- Implemented model export scripts for BiRefNet and HAT Sharper, ensuring proper weight compression and licensing.
- Created `deform_sampling.py` for deformable convolution operations used in BiRefNet.
- Added utility functions for compressing ONNX weights without altering graph arithmetic.
- Introduced a reference plane node for depth field adjustments in geometry processing.

tests/anyimage/server/test_job_server.py

@@ -63,7 +63,7 @@ class JobServerTest(ServerTestCase):
 
     def test_cancelling_job_keeps_server_and_model_cache_alive(self):
         fake_models = SimpleNamespace(
-            snapshot=lambda: {"loaded": {"ben2": "BEN2_BASE", "geometry": ""}},
+            snapshot=lambda: {"loaded": {"background": "BEN2_BASE", "geometry": ""}},
             clear=lambda: None,
             close=lambda: None,
         )
@@ -87,7 +87,7 @@ class JobServerTest(ServerTestCase):
         self.assertEqual(status["state"], "cancelled")
         self.assertFalse(server.shutdown_event.is_set())
         self.assertEqual(
-            server.snapshot("instance")["resources"]["model_manager"]["loaded"]["ben2"],
+            server.snapshot("instance")["resources"]["model_manager"]["loaded"]["background"],
             "BEN2_BASE",
         )