diff --git a/README.md b/README.md
index d3c027e6..79de8377 100644
--- a/README.md
+++ b/README.md
@@ -42,6 +42,7 @@ Self-Created Tools to convert ONNX files (NCHW) to TensorFlow format (NHWC). The
 8. Calculation error due to scaling up or down by specifying a `scale` when resizing images
 
 The above differences often cannot be dealt with by simply converting the model in a straightforward manner. Therefore, you need to replace the model yourself in advance with an operation that is less prone to errors.
+- [x] TFLite does not support `TrueDiv`(INT), so `TrueDiv` is avoided if possible.
 - [x] Implement the `Resize` process for the 5D tensor.
 - [x] Add process to replace `Asin` with `pseudo-Asin`.
 - [x] Add process to replace `Acos` with `pseudo-Acos`.
@@ -70,7 +71,7 @@ Video speed is adjusted approximately 50 times slower than actual speed.
 $ docker run --rm -it \
 -v `pwd`:/workdir \
 -w /workdir \
-ghcr.io/pinto0309/onnx2tf:1.0.25
+ghcr.io/pinto0309/onnx2tf:1.0.26
 
 or
 
diff --git a/onnx2tf/__init__.py b/onnx2tf/__init__.py
index e667fac1..c517b432 100644
--- a/onnx2tf/__init__.py
+++ b/onnx2tf/__init__.py
@@ -1,3 +1,3 @@
 from onnx2tf.onnx2tf import convert, main
 
-__version__ = '1.0.25'
+__version__ = '1.0.26'
diff --git a/onnx2tf/ops/Div.py b/onnx2tf/ops/Div.py
index a1b74b14..267ba69b 100644
--- a/onnx2tf/ops/Div.py
+++ b/onnx2tf/ops/Div.py
@@ -94,13 +94,18 @@ def make_node(
         const_or_var_2=input_tensor_2,
     )
 
+    # TFLite does not support TrueDiv(INT), so TrueDiv is avoided if possible
+    x_is_integer = input_tensor_1.dtype in target_cast_dtype
+    y_is_integer = input_tensor_2.dtype in target_cast_dtype
+    xy_is_integer = x_is_integer and y_is_integer
+
     divided_tensor = tf.math.divide(
-        x=input_tensor_1,
-        y=input_tensor_2,
+        x=input_tensor_1 if not xy_is_integer else tf.cast(input_tensor_1, dtype=tf.float32),
+        y=input_tensor_2 if not xy_is_integer else tf.cast(input_tensor_2, dtype=tf.float32),
         name=graph_node.name,
     )
 
-    if dtype in target_cast_dtype:
+    if xy_is_integer and dtype in target_cast_dtype:
         divided_tensor = tf.cast(divided_tensor, dtype=dtype)
 
     tf_layers_dict[graph_node_output.name]['tf_node'] = divided_tensor