Route non-interactive library messages through loggers

src/diffusers/models/autoencoders/vae.py

@@ -17,7 +17,7 @@
 import torch
 import torch.nn as nn
 
-from ...utils import BaseOutput
+from ...utils import BaseOutput, logging
 from ...utils.torch_utils import randn_tensor
 from ..activations import get_activation
 from ..attention_processor import SpatialNorm
@@ -29,6 +29,9 @@
 )
 
 
+logger = logging.get_logger(__name__)
+
+
 @dataclass
 class EncoderOutput(BaseOutput):
     r"""
@@ -599,7 +602,7 @@ def __init__(
             if self.unknown_index == "extra":
                 self.unknown_index = self.re_embed
                 self.re_embed = self.re_embed + 1
-            print(
+            logger.info(
                 f"Remapping {self.n_e} indices to {self.re_embed} indices. "
                 f"Using {self.unknown_index} for unknown indices."
             )

src/diffusers/pipelines/longcat_image/pipeline_longcat_image.py

@@ -110,15 +110,15 @@ def prepare_pos_ids(modality_id=0, type="text", start=(0, 0), num_token=None, he
     if type == "text":
         assert num_token
         if height or width:
-            print('Warning: The parameters of height and width will be ignored in "text" type.')
+            logger.warning('The parameters of height and width will be ignored in "text" type.')
         pos_ids = torch.zeros(num_token, 3)
         pos_ids[..., 0] = modality_id
         pos_ids[..., 1] = torch.arange(num_token) + start[0]
         pos_ids[..., 2] = torch.arange(num_token) + start[1]
     elif type == "image":
         assert height and width
         if num_token:
-            print('Warning: The parameter of num_token will be ignored in "image" type.')
+            logger.warning('The parameter of num_token will be ignored in "image" type.')
         pos_ids = torch.zeros(height, width, 3)
         pos_ids[..., 0] = modality_id
         pos_ids[..., 1] = pos_ids[..., 1] + torch.arange(height)[:, None] + start[0]

src/diffusers/pipelines/longcat_image/pipeline_longcat_image_edit.py

@@ -108,15 +108,15 @@ def prepare_pos_ids(modality_id=0, type="text", start=(0, 0), num_token=None, he
     if type == "text":
         assert num_token
         if height or width:
-            print('Warning: The parameters of height and width will be ignored in "text" type.')
+            logger.warning('The parameters of height and width will be ignored in "text" type.')
         pos_ids = torch.zeros(num_token, 3)
         pos_ids[..., 0] = modality_id
         pos_ids[..., 1] = torch.arange(num_token) + start[0]
         pos_ids[..., 2] = torch.arange(num_token) + start[1]
     elif type == "image":
         assert height and width
         if num_token:
-            print('Warning: The parameter of num_token will be ignored in "image" type.')
+            logger.warning('The parameter of num_token will be ignored in "image" type.')
         pos_ids = torch.zeros(height, width, 3)
         pos_ids[..., 0] = modality_id
         pos_ids[..., 1] = pos_ids[..., 1] + torch.arange(height)[:, None] + start[0]

src/diffusers/pipelines/wan/pipeline_wan_animate.py

@@ -569,7 +569,7 @@ def prepare_prev_segment_cond_latents(
         latent_height = height // self.vae_scale_factor_spatial
         latent_width = width // self.vae_scale_factor_spatial
         if segment_height != height or segment_width != width:
-            print(
+            logger.warning(
                 f"Interpolating prev segment cond video from ({segment_width}, {segment_height}) to ({width}, {height})"
             )
             # Perform a 4D (spatial) rather than a 5D (spatiotemporal) reshape, following the original code