diff --git a/esphome/components/esp32_camera/__init__.py b/esphome/components/esp32_camera/__init__.py
index f3c0e0f165..abbb4b1b7e 100644
--- a/esphome/components/esp32_camera/__init__.py
+++ b/esphome/components/esp32_camera/__init__.py
@@ -25,8 +25,6 @@ ESP32CameraFrameSize = esp32_camera_ns.enum("ESP32CameraFrameSize")
 FRAME_SIZES = {
     "160X120": ESP32CameraFrameSize.ESP32_CAMERA_SIZE_160X120,
     "QQVGA": ESP32CameraFrameSize.ESP32_CAMERA_SIZE_160X120,
-    "128X160": ESP32CameraFrameSize.ESP32_CAMERA_SIZE_128X160,
-    "QQVGA2": ESP32CameraFrameSize.ESP32_CAMERA_SIZE_128X160,
     "176X144": ESP32CameraFrameSize.ESP32_CAMERA_SIZE_176X144,
     "QCIF": ESP32CameraFrameSize.ESP32_CAMERA_SIZE_176X144,
     "240X176": ESP32CameraFrameSize.ESP32_CAMERA_SIZE_240X176,
diff --git a/esphome/components/esp32_camera/esp32_camera.cpp b/esphome/components/esp32_camera/esp32_camera.cpp
index 1d9faf7ea2..6bb57a8304 100644
--- a/esphome/components/esp32_camera/esp32_camera.cpp
+++ b/esphome/components/esp32_camera/esp32_camera.cpp
@@ -55,9 +55,6 @@ void ESP32Camera::dump_config() {
     case FRAMESIZE_QQVGA:
       ESP_LOGCONFIG(TAG, "  Resolution: 160x120 (QQVGA)");
       break;
-    case FRAMESIZE_QQVGA2:
-      ESP_LOGCONFIG(TAG, "  Resolution: 128x160 (QQVGA2)");
-      break;
     case FRAMESIZE_QCIF:
       ESP_LOGCONFIG(TAG, "  Resolution: 176x155 (QCIF)");
       break;
@@ -209,9 +206,6 @@ void ESP32Camera::set_frame_size(ESP32CameraFrameSize size) {
     case ESP32_CAMERA_SIZE_160X120:
       this->config_.frame_size = FRAMESIZE_QQVGA;
       break;
-    case ESP32_CAMERA_SIZE_128X160:
-      this->config_.frame_size = FRAMESIZE_QQVGA2;
-      break;
     case ESP32_CAMERA_SIZE_176X144:
       this->config_.frame_size = FRAMESIZE_QCIF;
       break;
diff --git a/esphome/components/esp32_camera/esp32_camera.h b/esphome/components/esp32_camera/esp32_camera.h
index fd8597d0c1..03272d3b32 100644
--- a/esphome/components/esp32_camera/esp32_camera.h
+++ b/esphome/components/esp32_camera/esp32_camera.h
@@ -37,7 +37,6 @@ class CameraImageReader {
 
 enum ESP32CameraFrameSize {
   ESP32_CAMERA_SIZE_160X120,    // QQVGA
-  ESP32_CAMERA_SIZE_128X160,    // QQVGA2
   ESP32_CAMERA_SIZE_176X144,    // QCIF
   ESP32_CAMERA_SIZE_240X176,    // HQVGA
   ESP32_CAMERA_SIZE_320X240,    // QVGA
diff --git a/tests/test4.yaml b/tests/test4.yaml
index fb2bce82a4..08213fab87 100644
--- a/tests/test4.yaml
+++ b/tests/test4.yaml
@@ -183,6 +183,23 @@ display:
     lambda: |-
       it.rectangle(0, 0, it.get_width(), it.get_height());
 
+esp32_camera:
+  name: ESP-32 Camera
+  data_pins: [GPIO17, GPIO35, GPIO34, GPIO5, GPIO39, GPIO18, GPIO36, GPIO19]
+  vsync_pin: GPIO22
+  href_pin: GPIO26
+  pixel_clock_pin: GPIO21
+  external_clock:
+    pin: GPIO27
+    frequency: 20MHz
+  i2c_pins:
+    sda: GPIO25
+    scl: GPIO23
+  reset_pin: GPIO15
+  power_down_pin: GPIO1
+  resolution: 640x480
+  jpeg_quality: 10
+
 external_components:
   - source: github://esphome/esphome@dev
     refresh: 1d