feat: update predict_noise_xl to use vector embedding from add_time_ids

tests/library/test_leco_train_util.py

@@ -1,5 +1,7 @@
 from pathlib import Path
 
+import torch
+
 from library.leco_train_util import load_prompt_settings
 
 
@@ -69,3 +71,44 @@ neutral: ""
 
     assert fourth.action == "enhance"
     assert fourth.multiplier == -1.25
+
+
+def test_predict_noise_xl_uses_vector_embedding_from_add_time_ids():
+    from library import sdxl_train_util
+    from library.leco_train_util import PromptEmbedsXL, predict_noise_xl
+
+    class DummyScheduler:
+        def scale_model_input(self, latent_model_input, timestep):
+            return latent_model_input
+
+    class DummyUNet:
+        def __call__(self, x, timesteps, context, y):
+            self.x = x
+            self.timesteps = timesteps
+            self.context = context
+            self.y = y
+            return torch.zeros_like(x)
+
+    latents = torch.randn(1, 4, 8, 8)
+    prompt_embeds = PromptEmbedsXL(
+        text_embeds=torch.randn(2, 77, 2048),
+        pooled_embeds=torch.randn(2, 1280),
+    )
+    add_time_ids = torch.tensor(
+        [
+            [1024, 1024, 0, 0, 1024, 1024],
+            [1024, 1024, 0, 0, 1024, 1024],
+        ],
+        dtype=prompt_embeds.pooled_embeds.dtype,
+    )
+
+    unet = DummyUNet()
+    noise_pred = predict_noise_xl(unet, DummyScheduler(), torch.tensor(10), latents, prompt_embeds, add_time_ids)
+
+    expected_size_embeddings = sdxl_train_util.get_size_embeddings(
+        add_time_ids[:, :2], add_time_ids[:, 2:4], add_time_ids[:, 4:6], latents.device
+    ).to(prompt_embeds.pooled_embeds.dtype)
+
+    assert noise_pred.shape == latents.shape
+    assert unet.context is prompt_embeds.text_embeds
+    assert torch.equal(unet.y, torch.cat([prompt_embeds.pooled_embeds, expected_size_embeddings], dim=1))