remove prints

Author: a-r-r-o-w

src/diffusers/models/modeling_utils.py

@@ -1178,7 +1178,7 @@ def from_pretrained(cls, pretrained_model_name_or_path: Optional[Union[str, os.P
             hf_quantizer.preprocess_model(
                 model=model, device_map=device_map, keep_in_fp32_modules=keep_in_fp32_modules
             )
-        print(keep_in_fp32_modules)
+
         # Now that the model is loaded, we can determine the device_map
         device_map = _determine_device_map(
             model, device_map, max_memory, torch_dtype, keep_in_fp32_modules, hf_quantizer

src/diffusers/pipelines/consisid/consisid_utils.py

@@ -8,9 +8,11 @@
 from torchvision.transforms import InterpolationMode
 from torchvision.transforms.functional import normalize, resize
 
-from ...utils import load_image
+from ...utils import get_logger, load_image
 
 
+logger = get_logger(__name__)
+
 _insightface_available = importlib.util.find_spec("insightface") is not None
 _consisid_eva_clip_available = importlib.util.find_spec("consisid_eva_clip") is not None
 _facexlib_available = importlib.util.find_spec("facexlib") is not None
@@ -166,7 +168,7 @@ def process_face_embeddings(
 
     # incase insightface didn't detect face
     if id_ante_embedding is None:
-        print("fail to detect face using insightface, extract embedding on align face")
+        logger.warning("Failed to detect face using insightface. Extracting embedding with align face")
         id_ante_embedding = face_helper_2.get_feat(align_face)
 
     id_ante_embedding = torch.from_numpy(id_ante_embedding).to(device, weight_dtype)  # torch.Size([512])