Overview

Parameters

• Refresh time: The refresh time is based on experimental test data, and there may be errors in the actual refresh time. The actual results shall prevail. There will be a flickering effect during the global refresh process, which is a normal phenomenon.
  

User Guide

Function Introduction

1. PWR button: Click this button to turn on the system power, and long press the button to turn off the system power; when the system power is on, click to enter sleep mode.
2. BOOT button: Switch images and enter download mode
3. KEY: Sleep mode wake-up, mode switching.
4. ACT indicator: Screen refresh, flashing
5. PWR indicator light: Operable indicator light, lights up to indicate that operation can be performed

Product Usage

1. First download the Demo in your own way, unzip it, and then copy all files from the sdcard directory to the sdcard (it is already set up by default out of the box)
2. Click the PWR button to turn on the device. The first time you turn it on, there will be a network pairing process, and the voice will announce "Enter networking mode." At this time, use your phone to connect to Xiaozhi-xxx (xxx represents a variable)
3. After the networking is successful, go to XiaoZhi Console to add the corresponding device

4. This product has three working modes, namely basic mode (Mode 1), LAN server mode (Mode 2), and AI conversation mode (Mode 3). The following will describe in detail how to use these three modes

Mode 1

1. The default mode is AI conversation mode (Mode 3). Press and hold the KEY button to enter mode selection (voice will be broadcasted), then click the KEY button to select basic mode (Mode 1). Press and hold the KEY button again to enter this mode
2. You can add the photos you want to display to the 06_user_Foundation_img directory on the TF card. It only accepts 800x480 or 480x800, 24-bit depth BMP format images. The images need to be dithered; for details, see Image Creation. If you're interested, you can also check out the code we provide, which also includes a dithering algorithm. Users can modify and use it as needed, as shown in the figure below:

3. Click the BOOT button to display images under the 06_user_Foundation_img directory. After displaying the images, it will automatically enter sleep mode.
4. You can wake up and switch images through the BOOT button, or you can click the KEY button to wake up without switching images.
5. When in sleep mode, there is a scheduled wake-up, which can be set through the config.txt file under the 06_user_Foundation_img directory. The specific code segment and file location are as follows:

Mode 2

1. If the product is in low-power mode, first press the KEY button to wake it up, then long press the KEY button to enter mode selection; double-click the KEY button, then long press again to enter this mode
2. Connect your phone or computer to Wi-Fi: esp_network, password: 1234567890. After a successful connection, go to the image selection interface, as shown in the figure:

3. Click the Input to select the corresponding image (the image must be a 24-bit deep 800x480 or 480x800 image, and it must be dithered). For more details, see Image Creation. Click Send to send the corresponding image to the frame
4. If you need to enter low power mode, you can directly disconnect the WIFI connection, and the product will wake up every 30 seconds. The specific code snippet is as follows, users can modify it themselves. After successfully connecting to WIFI, sleep mode is prohibited

Mode 3

Press and hold the KEY button to enter the mode selection, click the KEY button three times, and then press and hold the KEY button again to enter the mode
2. After initialization is complete, it will automatically obtain the weather forecast for the next 4 days
3. Wait until the screen display is complete to start the conversation. The wake-up word is "Hello, XiaoZhi".
4. After waking up, you can have a normal conversation
5. MCP can be used to display images of the 05_user_ai_img directory in the TF card through MCP, obtain the number of images in the 05_user_ai_img directory in the TF card and provide image ratings. The specific MCP service code is as follows, and users can DIY their own MCP service:

6. Regarding the use of AI-generated images, for example, you can say "help me generate an image of the moon". If you need to use this feature, you need to configure Volcano Engine​. For specific configuration details, refer to Volcano Engine Text-to-Image Configuration
7. After rating the images, they will be rotated every 30 minutes with the corresponding code as follows. The rating can be reset through voice commands

Volcano Engine Text-to-Image Configuration

1. Firstly, you need to obtain the key, model name, and URL. Currently, a test model is being used, which will be discontinued. Users will need to configure the model themselves. The relevant code segments and configurations in the config.txt file are as follows:


2. Go to the Volcano Engine Console

3. Create the corresponding model, remember not to select the wrong model, as shown in the figure:

4. Copy the corresponding key, model, and URL, as shown in the figure:

5. Paste the copied URL, model, and key into the corresponding key-value pairs in the config.txt file under the sdcard->06_user_Foundation_img directory (Step 1, Figure 2) (New users can get Tokens for free)

Picture Production

• To make a scatter plot with PS and other tools, please refer to: E-Paper Floyd-Steinberg
• Use the tools we have written to convert images, applications and source codes: Six-color dithering image conversion tool
  • The program converts images to appropriate resolutions and optimizes them using dithering algorithms, supports most formats of images, recognizes the orientation of images and automatically stretches and crops them
  • How to use: Drag and drop the picture directly onto "convert.exe" to convert a single image, or put all the images into a folder and then double-click "converterTo6color_all.cmd" for batch conversion
  • Note: This program is developed and open source for the convenience of customers only, and we do not provide technical support for it

Tools for Windows

• Conversion of a single image
  

Drag the image onto convert.exe

• Batch conversion of images
  

Put the images, convert.exe, and converterTo6color_all.cmd in a folder, and then double-click converterTo6color_all.cmd

Tools for MAC

Put the images, convert, and converterTo6color_all in a folder
Open the terminal and enter the corresponding folder

cd xxxx/xxx/xxx/

• Conversion of a single image
  

Enter the command to grant the convert executable permission

sudo chmod +x convert

Image conversion

./convert image name

• Batch conversion of images
  

You need to perform permission operations on the convert file first
Enter a command to give converterTo6color_all.sh executable permissions

sudo chmod +x converterTo6color_all.sh

Image conversion

./converterTo6color_all.sh

Development Description

• Note: This program is open source and does not provide technical support (please feel free to provide feedback if there are any bugs).
• The program is written in C/C++ SDK based on ESP-IDF, compiled using CMAKE, and theoretically supports multiple platforms. Please set up the relevant environment yourself.