diff --git a/boards/espressif/esp32s3_eye/esp32s3_eye_procpu.yaml b/boards/espressif/esp32s3_eye/esp32s3_eye_procpu.yaml
index adddce2e59e7ea..089082c42e505c 100644
--- a/boards/espressif/esp32s3_eye/esp32s3_eye_procpu.yaml
+++ b/boards/espressif/esp32s3_eye/esp32s3_eye_procpu.yaml
@@ -16,6 +16,7 @@ supported:
   - pwm
   - dma
   - input
+  - video
 testing:
   ignore_tags:
     - net
diff --git a/drivers/video/video_esp32_dvp.c b/drivers/video/video_esp32_dvp.c
index 54a480e5424d09..d11a209fed211f 100644
--- a/drivers/video/video_esp32_dvp.c
+++ b/drivers/video/video_esp32_dvp.c
@@ -89,7 +89,6 @@ void video_esp32_dma_rx_done(const struct device *dev, void *user_data, uint32_t
 			     int status)
 {
 	struct video_esp32_data *data = user_data;
-	int ret = 0;
 
 	if (status == DMA_STATUS_BLOCK) {
 		LOG_DBG("received block");
@@ -278,7 +277,6 @@ static int video_esp32_set_fmt(const struct device *dev, enum video_endpoint_id
 static int video_esp32_enqueue(const struct device *dev, enum video_endpoint_id ep,
 			       struct video_buffer *vbuf)
 {
-	const struct video_esp32_config *cfg = dev->config;
 	struct video_esp32_data *data = dev->data;
 
 	if (ep != VIDEO_EP_OUT) {
diff --git a/samples/drivers/video/capture/Kconfig b/samples/drivers/video/capture/Kconfig
new file mode 100644
index 00000000000000..5ec77c553e198e
--- /dev/null
+++ b/samples/drivers/video/capture/Kconfig
@@ -0,0 +1,27 @@
+# Copyright (c) 2024 Espressif Systems (Shanghai) Co., Ltd.
+# SPDX-License-Identifier: Apache-2.0
+
+mainmenu "Video capture sample application"
+
+menu "Video capture configuration"
+
+config VIDEO_FRAME_HEIGHT
+	int "Height of the video frame"
+	default 0
+	help
+	  Height of the video frame. If set to 0, the default height is used.
+
+config VIDEO_FRAME_WIDTH
+	int "Width of the video frame"
+	default 0
+	help
+	  Width of the video frame. If set to 0, the default width is used.
+
+config VIDEO_PIXEL_FORMAT
+	string "Pixel format of the video frame"
+	help
+	  Pixel format of the video frame. If not set, the default pixel format is used.
+
+endmenu
+
+source "Kconfig.zephyr"
diff --git a/samples/drivers/video/capture/boards/esp32s3_eye_procpu.conf b/samples/drivers/video/capture/boards/esp32s3_eye_procpu.conf
new file mode 100644
index 00000000000000..76321800fa069a
--- /dev/null
+++ b/samples/drivers/video/capture/boards/esp32s3_eye_procpu.conf
@@ -0,0 +1,11 @@
+CONFIG_VIDEO_BUFFER_POOL_SZ_MAX=40000
+CONFIG_VIDEO_BUFFER_POOL_NUM_MAX=3
+CONFIG_ESP_SPIRAM=y
+CONFIG_SPIRAM_MODE_OCT=y
+CONFIG_VIDEO_BUFFER_POOL_ALIGN=32
+CONFIG_DMA_ESP32_MAX_DESCRIPTOR_NUM=64
+CONFIG_VIDEO_BUFFER_USE_SHARED_MULTI_HEAP=y
+CONFIG_VIDEO_BUFFER_SMH_ATTRIBUTE=2
+CONFIG_VIDEO_FRAME_HEIGHT=240
+CONFIG_VIDEO_FRAME_WIDTH=240
+CONFIG_VIDEO_PIXEL_FORMAT="RGBP"
diff --git a/samples/drivers/video/capture/sample.yaml b/samples/drivers/video/capture/sample.yaml
index 6d3724b106ff39..79b65494bad55a 100644
--- a/samples/drivers/video/capture/sample.yaml
+++ b/samples/drivers/video/capture/sample.yaml
@@ -24,6 +24,7 @@ tests:
       - mimxrt1064_evk
       - mimxrt1170_evk/mimxrt1176/cm7
       - mm_swiftio
+      - esp32s3_eye/esp32s3/procpu
     depends_on: video
     integration_platforms:
       - mimxrt1064_evk
diff --git a/samples/drivers/video/capture/src/main.c b/samples/drivers/video/capture/src/main.c
index 9eed2a3924fb27..d2d64b84dd408d 100644
--- a/samples/drivers/video/capture/src/main.c
+++ b/samples/drivers/video/capture/src/main.c
@@ -22,18 +22,13 @@ static inline int display_setup(const struct device *const display_dev, const ui
 	struct display_capabilities capabilities;
 	int ret = 0;
 
-	if (!device_is_ready(display_dev)) {
-		LOG_ERR("Device %s not found", display_dev->name);
-		return -ENODEV;
-	}
-
-	printk("\nDisplay device: %s\n", display_dev->name);
+	LOG_INF("Display device: %s", display_dev->name);
 
 	display_get_capabilities(display_dev, &capabilities);
 
-	printk("- Capabilities:\n");
-	printk("  x_resolution = %u, y_resolution = %u, supported_pixel_formats = %u\n"
-	       "  current_pixel_format = %u, current_orientation = %u\n\n",
+	LOG_INF("- Capabilities:");
+	LOG_INF("  x_resolution = %u, y_resolution = %u, supported_pixel_formats = %u"
+	       "  current_pixel_format = %u, current_orientation = %u",
 	       capabilities.x_resolution, capabilities.y_resolution,
 	       capabilities.supported_pixel_formats, capabilities.current_pixel_format,
 	       capabilities.current_orientation);
@@ -41,7 +36,7 @@ static inline int display_setup(const struct device *const display_dev, const ui
 	/* Set display pixel format to match the one in use by the camera */
 	switch (pixfmt) {
 	case VIDEO_PIX_FMT_RGB565:
-		ret = display_set_pixel_format(display_dev, PIXEL_FORMAT_BGR_565);
+		ret = display_set_pixel_format(display_dev, PIXEL_FORMAT_RGB_565);
 		break;
 	case VIDEO_PIX_FMT_XRGB32:
 		ret = display_set_pixel_format(display_dev, PIXEL_FORMAT_ARGB_8888);
@@ -101,7 +96,7 @@ int main(void)
 	}
 #endif
 
-	printk("Video device: %s\n", video_dev->name);
+	LOG_INF("Video device: %s", video_dev->name);
 
 	/* Get capabilities */
 	if (video_get_caps(video_dev, VIDEO_EP_OUT, &caps)) {
@@ -109,11 +104,11 @@ int main(void)
 		return 0;
 	}
 
-	printk("- Capabilities:\n");
+	LOG_INF("- Capabilities:");
 	while (caps.format_caps[i].pixelformat) {
 		const struct video_format_cap *fcap = &caps.format_caps[i];
 		/* fourcc to string */
-		printk("  %c%c%c%c width [%u; %u; %u] height [%u; %u; %u]\n",
+		LOG_INF("  %c%c%c%c width [%u; %u; %u] height [%u; %u; %u]",
 		       (char)fcap->pixelformat, (char)(fcap->pixelformat >> 8),
 		       (char)(fcap->pixelformat >> 16), (char)(fcap->pixelformat >> 24),
 		       fcap->width_min, fcap->width_max, fcap->width_step, fcap->height_min,
@@ -127,23 +122,43 @@ int main(void)
 		return 0;
 	}
 
-	printk("- Default format: %c%c%c%c %ux%u\n", (char)fmt.pixelformat,
+#if CONFIG_VIDEO_FRAME_HEIGHT
+	fmt.height = CONFIG_VIDEO_FRAME_HEIGHT;
+#endif
+
+#if CONFIG_VIDEO_FRAME_WIDTH
+	fmt.width = CONFIG_VIDEO_FRAME_WIDTH;
+	fmt.pitch = fmt.width * 2;
+#endif
+
+	if (strcmp(CONFIG_VIDEO_PIXEL_FORMAT, "")) {
+		fmt.pixelformat =
+			video_fourcc(CONFIG_VIDEO_PIXEL_FORMAT[0], CONFIG_VIDEO_PIXEL_FORMAT[1],
+				     CONFIG_VIDEO_PIXEL_FORMAT[2], CONFIG_VIDEO_PIXEL_FORMAT[3]);
+	}
+
+	LOG_INF("- Video format: %c%c%c%c %ux%u", (char)fmt.pixelformat,
 	       (char)(fmt.pixelformat >> 8), (char)(fmt.pixelformat >> 16),
 	       (char)(fmt.pixelformat >> 24), fmt.width, fmt.height);
 
+	if (video_set_format(video_dev, VIDEO_EP_OUT, &fmt)) {
+		LOG_ERR("Unable to set format");
+		return 0;
+	}
+
 	if (!video_get_frmival(video_dev, VIDEO_EP_OUT, &frmival)) {
-		printk("- Default frame rate : %f fps\n",
+		LOG_INF("- Default frame rate : %f fps",
 		       1.0 * frmival.denominator / frmival.numerator);
 	}
 
-	printk("- Supported frame intervals for the default format:\n");
+	LOG_INF("- Supported frame intervals for the default format:");
 	memset(&fie, 0, sizeof(fie));
 	fie.format = &fmt;
 	while (video_enum_frmival(video_dev, VIDEO_EP_OUT, &fie) == 0) {
 		if (fie.type == VIDEO_FRMIVAL_TYPE_DISCRETE) {
-			printk("   %u/%u ", fie.discrete.numerator, fie.discrete.denominator);
+			LOG_INF("   %u/%u ", fie.discrete.numerator, fie.discrete.denominator);
 		} else {
-			printk("   [min = %u/%u; max = %u/%u; step = %u/%u]\n",
+			LOG_INF("   [min = %u/%u; max = %u/%u; step = %u/%u]",
 			       fie.stepwise.min.numerator, fie.stepwise.min.denominator,
 			       fie.stepwise.max.numerator, fie.stepwise.max.denominator,
 			       fie.stepwise.step.numerator, fie.stepwise.step.denominator);
@@ -190,7 +205,7 @@ int main(void)
 		return 0;
 	}
 
-	printk("Capture started\n");
+	LOG_INF("Capture started");
 
 	/* Grab video frames */
 	while (1) {
@@ -200,7 +215,7 @@ int main(void)
 			return 0;
 		}
 
-		printk("Got frame %u! size: %u; timestamp %u ms\n", frame++, vbuf->bytesused,
+		LOG_DBG("Got frame %u! size: %u; timestamp %u ms", frame++, vbuf->bytesused,
 		       vbuf->timestamp);
 
 #if DT_HAS_CHOSEN(zephyr_display)