From 40129e8b098f375886f675327c0f981c750848da Mon Sep 17 00:00:00 2001 From: ChairC <974833488@qq.com> Date: Sat, 24 Feb 2024 20:12:44 +0800 Subject: [PATCH] Update: Modify Chinese introduction errors and add --image_format parameter introduction. --- README.md | 1 + README_zh.md | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 60ed98c..ed515df 100644 --- a/README.md +++ b/README.md @@ -318,6 +318,7 @@ The training GPU implements environment for this README is as follows: models ar | --conditional | | Enable conditional generation | bool | If enabled, allows custom configuration, such as modifying classes or classifier-free guidance interpolation weights | | --generate_name | | File name | str | File name to initialize the model for saving purposes | | --image_size | | Input image size | int | Size of input images, adaptive input/output size. if class name is -1 and conditional is True, the model would output one image per class. | +| --image_format | | Generated image format | str | Generated image format, jpg/png/jpeg. Recommend to use png for better generation quality. | | --num_images | | Number of generated images | int | Number of images to generate | | --weight_path | | Path to model weights | str | Path to the model weights file, required for network generation | | --result_path | | Save path | str | Path to save the generated images | diff --git a/README_zh.md b/README_zh.md index 7475c22..e675491 100644 --- a/README_zh.md +++ b/README_zh.md @@ -32,7 +32,7 @@ 该扩散模型为经典的ddpm和ddim,来源于论文《**[Denoising Diffusion Probabilistic Models](https://arxiv.org/abs/2006.11239)**》和《**[Denoising Diffusion Implicit Models](https://arxiv.org/abs/2010.02502)**》。 -我们将此项目命名为IDDM: Integrated Design Diffusion Model,中文名为集成设计缺陷扩散模型。在此项目中进行模型复现、训练器和生成器编写、部分算法和网络结构的改进与优化,该仓库**持续维护**。 +我们将此项目命名为IDDM: Integrated Design Diffusion Model,中文名为集成设计扩散模型。在此项目中进行模型复现、训练器和生成器编写、部分算法和网络结构的改进与优化,该仓库**持续维护**。 如果有任何问题,请先到此[**issue**](https://github.com/chairc/Integrated-Design-Diffusion-Model/issues/9)进行问题查询,若无法解决可以加入我们的QQ群:949120343、开启新issue提问或联系我的邮箱:chenyu1998424@gmail.com/chairc1998@163.com @@ -316,6 +316,7 @@ Integrated Design Diffusion Model | --conditional | | 开启条件生成 | bool | 若开启可修改自定义配置,例如修改类别、classifier-free guidance插值权重 | | --generate_name | | 文件名称 | str | 初始化模型的文件名称,用于设置保存信息 | | --image_size | | 输入图像大小 | int | 输入图像大小,自适应输入输出尺寸。如果输入为-1并且开启条件生成为真,则模型为每类输出一张图片 | +| --image_format | | 生成图片格式 | str | 生成图片格式,jpg/png/jpeg等。推荐使用png获取更好的生产质量 | | --num_images | | 生成图片个数 | int | 单次生成图片个数 | | --weight_path | | 权重路径 | str | 模型权重路径,网络生成需要加载文件 | | --result_path | | 保存路径 | str | 保存路径 |