Update model recommendations in READMEs (#62)

- Update `README.md` to recommend "Nano Banana (non-Pro)" for Asset Extraction, with "Nano Banana Pro" as a fallback.
- Update `README_CN.md` with the same recommendation translated into Chinese.
- Fix typo "Nanao" to "Nano" in `README_CN.md` and ensure consistent use of "Nano Banana Pro".

Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>

README.md

@@ -82,7 +82,7 @@ For image generation, Nano Banana Pro delivers the highest-quality results and i
 
 Keep in mind that Nano Banana (non-Pro) may struggle during the look generation step, especially when the prompt includes multiple pieces of equipment or complex visual elements.
 
-For **Extract Asset** step, Nano Banana (non-Pro) is good enough, do not use Banana Pro.
+For the **Extract Asset** step, **Nano Banana (non-Pro)** is typically good enough for most cases. We recommend starting with it; if you are not satisfied with the result, you can re-extract using **Nano Banana Pro**.
 
 ## Data Backup
 

README_CN.md

@@ -78,11 +78,11 @@ Forgery 需要 AI 生成服务的 API 密钥（Google Gemini 和/或 OpenAI）
 
 对于文本生成，Gemini 3 Flash 或 GPT-5 Mini 通常足以满足大多数用例。
 
-对于图像生成，Nanao Banana Pro 提供最高质量的结果，通常是最佳选择。但是，如果考虑到成本，你可以考虑 Nano Banana (non-Pro) 或 GPT Image 1.5 作为更经济实惠的替代方案。
+对于图像生成，Nano Banana Pro 提供最高质量的结果，通常是最佳选择。但是，如果考虑到成本，你可以考虑 Nano Banana (non-Pro) 或 GPT Image 1.5 作为更经济实惠的替代方案。
 
 请记住，Nano Banana (non-Pro) 在 Look 生成步骤中可能会遇到困难，特别是当提示包含多个装备或复杂的视觉元素时。
 
-对于 **Extract Asset** 步骤，Nano Banana (non-Pro) 已经足够好，请勿使用 Banana Pro。
+对于 **Extract Asset** 步骤，**Nano Banana (non-Pro)** 通常已经足够。建议先尝试使用它；如果对结果不满意，可以使用 **Nano Banana Pro** 重新提取。
 
 ## 数据备份