Fix typos in text_to_image examples (#7050)

Update copyright information and fix typos in text_to_image examples

examples/text_to_image/README.md

@@ -4,7 +4,7 @@ The `train_text_to_image.py` script shows how to fine-tune stable diffusion mode
 
 ___Note___:
 
-___This script is experimental. The script fine-tunes the whole model and often times the model overfits and runs into issues like catastrophic forgetting. It's recommended to try different hyperparamters to get the best result on your dataset.___
+___This script is experimental. The script fine-tunes the whole model and often times the model overfits and runs into issues like catastrophic forgetting. It's recommended to try different hyperparameters to get the best result on your dataset.___
 
 
 ## Running locally with PyTorch

examples/text_to_image/README_sdxl.md

@@ -2,7 +2,7 @@
 
 The `train_text_to_image_sdxl.py` script shows how to fine-tune Stable Diffusion XL (SDXL) on your own dataset.
 
-🚨 This script is experimental. The script fine-tunes the whole model and often times the model overfits and runs into issues like catastrophic forgetting. It's recommended to try different hyperparamters to get the best result on your dataset. 🚨
+🚨 This script is experimental. The script fine-tunes the whole model and often times the model overfits and runs into issues like catastrophic forgetting. It's recommended to try different hyperparameters to get the best result on your dataset. 🚨
 
 ## Running locally with PyTorch
 
@@ -238,8 +238,8 @@ accelerate launch  --config_file $ACCELERATE_CONFIG_FILE train_text_to_image_lor
   --validation_epochs=20 \
   --seed=1234 \
   --output_dir="sd-pokemon-model-lora-sdxl" \
-  --validation_prompt="cute dragon creature" 
-  
+  --validation_prompt="cute dragon creature"
+
 ```
 
 

examples/text_to_image/test_text_to_image.py

+#!/usr/bin/env python
 # coding=utf-8
-# Copyright 2024 HuggingFace Inc.
+# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

examples/text_to_image/test_text_to_image_lora.py

+#!/usr/bin/env python
 # coding=utf-8
-# Copyright 2024 HuggingFace Inc.
+# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

examples/text_to_image/train_text_to_image.py

@@ -12,6 +12,7 @@
 # distributed under the License is distributed on an "AS IS" BASIS,
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
+# limitations under the License.
 
 import argparse
 import logging
@@ -395,7 +396,7 @@ def parse_args():
         "--prediction_type",
         type=str,
         default=None,
-        help="The prediction_type that shall be used for training. Choose between 'epsilon' or 'v_prediction' or leave `None`. If left to `None` the default prediction type of the scheduler: `noise_scheduler.config.prediciton_type` is chosen.",
+        help="The prediction_type that shall be used for training. Choose between 'epsilon' or 'v_prediction' or leave `None`. If left to `None` the default prediction type of the scheduler: `noise_scheduler.config.prediction_type` is chosen.",
     )
     parser.add_argument(
         "--hub_model_id",
@@ -635,7 +636,7 @@ def main():
                 ema_unet.to(accelerator.device)
                 del load_model
 
-            for i in range(len(models)):
+            for _ in range(len(models)):
                 # pop models so that they are not loaded again
                 model = models.pop()
 
@@ -810,7 +811,7 @@ def main():
     if args.use_ema:
         ema_unet.to(accelerator.device)
 
-    # For mixed precision training we cast all non-trainable weigths (vae, non-lora text_encoder and non-lora unet) to half-precision
+    # For mixed precision training we cast all non-trainable weights (vae, non-lora text_encoder and non-lora unet) to half-precision
     # as these weights are only used for inference, keeping weights in full precision is not required.
     weight_dtype = torch.float32
     if accelerator.mixed_precision == "fp16":

examples/text_to_image/train_text_to_image_flax.py

+#!/usr/bin/env python
+# coding=utf-8
+# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
 import argparse
 import logging
 import math

examples/text_to_image/train_text_to_image_lora.py

+#!/usr/bin/env python
 # coding=utf-8
 # Copyright 2024 The HuggingFace Inc. team. All rights reserved.
 #
@@ -293,7 +294,7 @@ def parse_args():
         "--prediction_type",
         type=str,
         default=None,
-        help="The prediction_type that shall be used for training. Choose between 'epsilon' or 'v_prediction' or leave `None`. If left to `None` the default prediction type of the scheduler: `noise_scheduler.config.prediciton_type` is chosen.",
+        help="The prediction_type that shall be used for training. Choose between 'epsilon' or 'v_prediction' or leave `None`. If left to `None` the default prediction type of the scheduler: `noise_scheduler.config.prediction_type` is chosen.",
     )
     parser.add_argument(
         "--hub_model_id",
@@ -454,7 +455,7 @@ def main():
     vae.requires_grad_(False)
     text_encoder.requires_grad_(False)
 
-    # For mixed precision training we cast all non-trainable weigths (vae, non-lora text_encoder and non-lora unet) to half-precision
+    # For mixed precision training we cast all non-trainable weights (vae, non-lora text_encoder and non-lora unet) to half-precision
     # as these weights are only used for inference, keeping weights in full precision is not required.
     weight_dtype = torch.float32
     if accelerator.mixed_precision == "fp16":

examples/text_to_image/train_text_to_image_lora_sdxl.py

@@ -370,7 +370,7 @@ def parse_args(input_args=None):
         "--prediction_type",
         type=str,
         default=None,
-        help="The prediction_type that shall be used for training. Choose between 'epsilon' or 'v_prediction' or leave `None`. If left to `None` the default prediction type of the scheduler: `noise_scheduler.config.prediciton_type` is chosen.",
+        help="The prediction_type that shall be used for training. Choose between 'epsilon' or 'v_prediction' or leave `None`. If left to `None` the default prediction type of the scheduler: `noise_scheduler.config.prediction_type` is chosen.",
     )
     parser.add_argument(
         "--hub_model_id",
@@ -585,7 +585,7 @@ def main(args):
     text_encoder_two.requires_grad_(False)
     unet.requires_grad_(False)
 
-    # For mixed precision training we cast all non-trainable weigths (vae, non-lora text_encoder and non-lora unet) to half-precision
+    # For mixed precision training we cast all non-trainable weights (vae, non-lora text_encoder and non-lora unet) to half-precision
     # as these weights are only used for inference, keeping weights in full precision is not required.
     weight_dtype = torch.float32
     if accelerator.mixed_precision == "fp16":
@@ -648,7 +648,7 @@ def main(args):
     def save_model_hook(models, weights, output_dir):
         if accelerator.is_main_process:
             # there are only two options here. Either are just the unet attn processor layers
-            # or there are the unet and text encoder atten layers
+            # or there are the unet and text encoder attn layers
             unet_lora_layers_to_save = None
             text_encoder_one_lora_layers_to_save = None
             text_encoder_two_lora_layers_to_save = None

examples/text_to_image/train_text_to_image_sdxl.py

@@ -419,7 +419,7 @@ def parse_args(input_args=None):
         "--prediction_type",
         type=str,
         default=None,
-        help="The prediction_type that shall be used for training. Choose between 'epsilon' or 'v_prediction' or leave `None`. If left to `None` the default prediction type of the scheduler: `noise_scheduler.config.prediciton_type` is chosen.",
+        help="The prediction_type that shall be used for training. Choose between 'epsilon' or 'v_prediction' or leave `None`. If left to `None` the default prediction type of the scheduler: `noise_scheduler.config.prediction_type` is chosen.",
     )
     parser.add_argument(
         "--hub_model_id",
@@ -683,7 +683,7 @@ def main(args):
     # Set unet as trainable.
     unet.train()
 
-    # For mixed precision training we cast all non-trainable weigths to half-precision
+    # For mixed precision training we cast all non-trainable weights to half-precision
     # as these weights are only used for inference, keeping weights in full precision is not required.
     weight_dtype = torch.float32
     if accelerator.mixed_precision == "fp16":
@@ -738,7 +738,7 @@ def main(args):
                 ema_unet.to(accelerator.device)
                 del load_model
 
-            for i in range(len(models)):
+            for _ in range(len(models)):
                 # pop models so that they are not loaded again
                 model = models.pop()
 
@@ -962,7 +962,7 @@ def main(args):
     if accelerator.is_main_process:
         accelerator.init_trackers("text2image-fine-tune-sdxl", config=vars(args))
 
-    # Function for unwraping if torch.compile() was used in accelerate.
+    # Function for unwrapping if torch.compile() was used in accelerate.
     def unwrap_model(model):
         model = accelerator.unwrap_model(model)
         model = model._orig_mod if is_compiled_module(model) else model