fix readme

README.md

@@ -10,8 +10,15 @@
 
 ### 介绍
 
-使用moondream等模型描述图片主要信息，同时使用了`wd-swinv2-tagger-v3`模型增加人物描述的准确性。
-使用了`hahahafofo/Qwen-1_8B-Stable-Diffusion-Prompt`充分利用Qwen的能力，支持包括古诗词在内的多种形式进行提示语的生成，此模型基于35k 条数据进行特定于任务的微调(SFT).
+
+- 我们采用了`wd-swinv2-tagger-v3`模型，显著提升了人物特征的描述准确度，特别适用于需要细腻描绘人物的场景。
+- 对于场景描写，`moondream1`模型提供了丰富的细节，但有时候可能显得冗长并缺乏准确性。相比之下，`moondream2`模型以其简洁而精确的场景描述脱颖而出。因此，在使用`Image2TextWithTags`节点时，对于以场景为主的文本生成，推荐`moondream1`与`wd-swinv2-tagger-v3`的组合；而对于注重人物描述的内容，`wd-swinv2-tagger-v3`与`moondream2`的搭配将是理想选择。
+- `Text2GPTPrompt`节点旨在创造高效的Prompt，该Prompt能够融合`moondream`系列模型和`wd-swinv2-tagger-v3`产生的关键词，为7b级别的模型定制，内含`qwen1.5-7b`。
+- 利用`hahahafofo/Qwen-1_8B-Stable-Diffusion-Prompt`模型，我们能够充分发挥Qwen的潜力，特别是在生成包括古诗词在内的各式提示语时展现卓越性能。此模型经过35000条数据的特定任务微调(SFT)，不仅性价比高，而且在CPU上运行的速度也相当可观。
+
+
+
+
 
 ### 第1步：安装插件
 
@@ -48,8 +55,10 @@ huggingface-cli download --resume-download unum-cloud/uform-gen2-qwen-500m --loc
 
 
 
-Models such as `moondream` are used to describe the main information of the image, and the `wd-swinv2-tagger-v3` model is used to increase the accuracy of character description.
-Used `hahahafofo/Qwen-1_8B-Stable-Diffusion-Prompt` to make full use of Qwen's capabilities and support multiple forms of prompt generation including ancient poetry. This model is based on 35k pieces of data for task-specific fine-tuning ( SFT).
+- We adopted the `wd-swinv2-tagger-v3` model, which significantly enhanced the accuracy of character trait descriptions, making it particularly suitable for scenarios requiring detailed depiction of characters.
+- For scene description, the `moondream1` model offers rich details but might sometimes appear verbose and lack precision. In contrast, the `moondream2` model stands out for its concise and accurate scene descriptions. Therefore, when using the `Image2TextWithTags` node, for text generation centered on scenes, a combination of `moondream1` and `wd-swinv2-tagger-v3` is recommended; for content focusing on character descriptions, pairing `wd-swinv2-tagger-v3` with `moondream2` is the ideal choice.
+- The `Text2GPTPrompt` node is designed to create efficient prompts that can integrate keywords generated by the `moondream` series models and `wd-swinv2-tagger-v3`, customized for models at the 7b level, including `qwen1.5-7b`.
+- Utilizing the `hahahafofo/Qwen-1_8B-Stable-Diffusion-Prompt` model, we can fully leverage the potential of Qwen, especially in generating various forms of prompts, including classical poetry. This model, fine-tuned with 35,000 pieces of data for specific tasks (SFT), not only offers a high cost-performance ratio but also runs at a considerable speed on CPUs.
 
 ### Step 1: Install the Plugin