chore: log schedulers; enforce DDIM in get_bald each call

Hair_stable_new_fresh/infer_full.py

@@ -1,4 +1,5 @@
 import torch
+import logging
 from PIL import Image
 import numpy as np
 from PIL import Image
@@ -63,6 +64,7 @@ def concatenate_images(image_files, output_file, type="pil"):
 class StableHair:
     def __init__(self, config="./configs/hair_transfer.yaml", device="cuda", weight_dtype=torch.float32) -> None:
         print("Initializing Stable Hair Pipeline...")
+        self.logger = logging.getLogger("hair_model")
         self.config = OmegaConf.load(config)
         self.device = device
         
@@ -176,6 +178,12 @@ class StableHair:
             self.remove_hair_pipeline.scheduler = _DDIM.from_config(self.remove_hair_pipeline.scheduler.config)
         except Exception:
             pass
+        # Log scheduler to confirm
+        try:
+            sched_name = type(self.remove_hair_pipeline.scheduler).__name__
+            self.logger.info(f"remove_hair_pipeline scheduler: {sched_name}")
+        except Exception:
+            pass
         image = self.remove_hair_pipeline(
             prompt="",
             negative_prompt="",

Hair_stable_new_fresh/server.py

@@ -180,6 +180,13 @@ def get_hairswap(req: HairSwapRequest, _=Depends(verify_bearer)):
         # Perform hair transfer with error handling
         try:
             LOGGER.info("Starting hair transfer...")
+            # Log current schedulers for visibility
+            try:
+                sched_main = type(model.pipeline.scheduler).__name__ if hasattr(model, "pipeline") else None
+                sched_bald = type(model.remove_hair_pipeline.scheduler).__name__ if hasattr(model, "remove_hair_pipeline") else None
+                LOGGER.info(f"Schedulers -> main: {sched_main}, remove_hair: {sched_bald}")
+            except Exception:
+                pass
             id_np, out_np, bald_np, ref_np = model.Hair_Transfer(
                 source_image=source_path,
                 reference_image=reference_path,