适配小米手机，更新 1.0.2 实测性能

README.md

@@ -19,7 +19,7 @@ tags:
 <div align="center">
 <h1>📱 NanoAvatar</h1>
 <h3>Changing how often avatar applications can be used and how many users they can serve</h3>
-<p>📱 <strong>Snapdragon 8 Gen 3 · Lite 37 FPS</strong> · ⚡ <strong>112 ms model first frame</strong></p>
+<p>📱 <strong>2023 mobile chipset · 41 FPS</strong> · ⚡ <strong>103 ms first-frame latency</strong></p>
 <p>
 <a href="https://github.com/wpydcr/NanoAvatar/releases"><strong>📱 Android downloads (Full / Lite)</strong></a> ·
 <a href="https://github.com/wpydcr/NanoAvatar"><strong>💻 Code and usage</strong></a>
@@ -31,7 +31,7 @@ English · <a href="https://huggingface.co/wpydcr/NanoAvatar/blob/main/README.zh
 </p>
 </div>
 
-**Try it offline, without an API key.** The app includes the models and an avatar. Record your voice to animate it. [Android guide](https://github.com/wpydcr/NanoAvatar#run-on-android).
+**Generate high-fidelity talking-avatar videos directly on your phone, without a cloud GPU.**
 
 <a id="demo"></a>
 ## 🎬 Demos
@@ -53,15 +53,16 @@ English · <a href="https://huggingface.co/wpydcr/NanoAvatar/blob/main/README.zh
   </tr>
 </table>
 
-**Generate high-fidelity talking-avatar videos directly on your phone, without a cloud GPU.**
+**Try the on-device avatar generation model offline.** The app includes the models and an avatar. Record your voice to animate it. [Android guide](https://github.com/wpydcr/NanoAvatar#run-on-android).
 
 <a id="performance"></a>
 ## 📊 Performance
 
-| Model | Device | Best model FPS | Best first frame | Memory / VRAM estimate |
+| Model | Device | Model FPS | First frame | Memory / VRAM estimate |
 | --- | --- | ---: | ---: | ---: |
-| 📱 NanoAvatar | **Z60 Ultra · Snapdragon 8 Gen 3**<br>Android 14 | **35 FPS** | **127 ms** | **834 MiB** |
-| 📱 NanoAvatar Lite | **Z60 Ultra · Snapdragon 8 Gen 3**<br>Android 14 | **37 FPS** | **112 ms** | **700 MiB** |
+| 📱 NanoAvatar | **2023 · Snapdragon 8 Gen 3**<br>Android 14 | **39 FPS** | **115 ms** | **834 MiB** |
+| 📱 NanoAvatar Lite | **2023 · Snapdragon 8 Gen 3**<br>Android 14 | **41 FPS** | **103 ms** | **700 MiB** |
+| 📱 NanoAvatar Lite | **2021 · Snapdragon 8 Gen 1**<br>Android 15 | **18 FPS** | **183 ms** | **693 MiB** |
 | ⚡ Quantized | **RTX 4090**<br>Windows CUDA | **333 FPS** | **18 ms** | **834 MiB** |
 | 🖥️ Full precision | **RTX 4090**<br>Windows CUDA | **224 FPS** | **37 ms** | **1119 MiB** |
 

README.zh-CN.md

@@ -1,7 +1,7 @@
 <div align="center">
 <h1>📱 NanoAvatar</h1>
 <h3>改变了数字人应用的使用频率和规模上限</h3>
-<p>📱 <strong>骁龙 8 Gen 3 · Lite 37 FPS</strong> · ⚡ <strong>模型首帧 112 ms</strong></p>
+<p>📱 <strong>23年手机芯片 · 41 FPS</strong> · ⚡ <strong>首帧延迟 103 ms</strong></p>
 <p>
 <a href="https://github.com/wpydcr/NanoAvatar/releases"><strong>📱 下载 Android App（完整版 / Lite）</strong></a> ·
 <a href="https://github.com/wpydcr/NanoAvatar/blob/main/README.zh-CN.md"><strong>💻 源码与使用说明</strong></a>
@@ -13,8 +13,7 @@
 </p>
 </div>
 
-**无需 API key，断网也能体验。** App 内置模型和人物，录音即可驱动数字人。[安卓使用说明](https://github.com/wpydcr/NanoAvatar/blob/main/README.zh-CN.md#run-on-android)。
-
+**直接在手机上生成高保真数字人视频，无需云端 GPU。**
 
 <a id="demo"></a>
 ## 🎬 实际效果
@@ -36,15 +35,18 @@
   </tr>
 </table>
 
-**直接在手机上生成高保真数字人视频，无需云端 GPU。**
+
+**断网体验端侧数字人生成模型。** App 内置模型和人物，录音即可驱动数字人。[安卓使用说明](https://github.com/wpydcr/NanoAvatar/blob/main/README.zh-CN.md#run-on-android)。
+
 
 <a id="performance"></a>
 ## 📊 性能实测
 
-| 模型 | 设备 | 最佳模型 FPS | 最佳首帧 | 内存 / 显存估算 |
+| 模型 | 设备 | 模型 FPS | 首帧 | 内存 / 显存估算 |
 | --- | --- | ---: | ---: | ---: |
-| 📱 NanoAvatar 完整版 | **Z60 Ultra · 骁龙 8 Gen 3**<br>Android 14 | **35 FPS** | **127 ms** | **834 MiB** |
-| 📱 NanoAvatar Lite | **Z60 Ultra · 骁龙 8 Gen 3**<br>Android 14 | **37 FPS** | **112 ms** | **700 MiB** |
+| 📱 NanoAvatar 完整版 | **23年 · 骁龙 8 Gen 3**<br>Android 14 | **39 FPS** | **115 ms** | **834 MiB** |
+| 📱 NanoAvatar Lite | **23年 · 骁龙 8 Gen 3**<br>Android 14 | **41 FPS** | **103 ms** | **700 MiB** |
+| 📱 NanoAvatar Lite | **21年 · 骁龙 8 Gen 1**<br>Android 15 | **18 FPS** | **183 ms** | **693 MiB** |
 | ⚡ 量化版 | **RTX 4090**<br>Windows CUDA | **333 FPS** | **18 ms** | **834 MiB** |
 | 🖥️ 满血版 | **RTX 4090**<br>Windows CUDA | **224 FPS** | **37 ms** | **1119 MiB** |