From 837abfc6f1eba18c23904377b964d4d9fa60e2c4 Mon Sep 17 00:00:00 2001
From: unknown <you@example.com>
Date: Thu, 16 Oct 2025 00:16:39 +0800
Subject: [PATCH] Add README files and requirements

---
 README.md        | 54 ++++++++++++++++++++++++++++++++++++++++++++++++
 README_cn.md     | 54 ++++++++++++++++++++++++++++++++++++++++++++++++
 requirements.txt |  8 +++++++
 3 files changed, 116 insertions(+)
 create mode 100644 README.md
 create mode 100644 README_cn.md
 create mode 100644 requirements.txt

diff --git a/README.md b/README.md
new file mode 100644
index 0000000..3dda78e
--- /dev/null
+++ b/README.md
@@ -0,0 +1,54 @@
+# ComfyUI_RH_mammothmoda
+
+ComfyUI custom nodes for MammothModa2 text-to-image generation.
+
+## Features
+
+- **Text-to-Image Generation**: High-quality image synthesis using MammothModa2
+- **Optimized Performance**: INT8 quantization support for efficient inference
+- **Flash Attention**: Enhanced speed with flash_attention_2
+
+## Installation
+
+### Via ComfyUI Manager (Recommended)
+Search for "RunningHub Mammothmoda" in ComfyUI Manager and install.
+
+### Manual Installation
+```bash
+cd ComfyUI/custom_nodes
+git clone https://github.com/HM-RunningHub/ComfyUI_RH_mammothmoda.git
+cd ComfyUI_RH_mammothmoda
+pip install -r requirements.txt
+```
+
+## Model Download
+
+Download the MammothModa2-Preview model and place it in:
+```
+ComfyUI/models/MammothModa2-Preview/
+```
+
+Model source: Check official MammothModa2 repository for model weights.
+
+## Usage
+
+1. **Load Model**: Use "RunningHub Mammothmoda Loader" node
+2. **Generate Image**: Connect to "RunningHub Mammothmoda T2I Sampler" node
+3. **Configure**: Set prompt, size (width/height), steps, and guidance scales
+4. **Run**: Execute workflow to generate images
+
+## Nodes
+
+- **RunningHub Mammothmoda Loader**: Loads the MammothModa2 model
+- **RunningHub Mammothmoda T2I Sampler**: Generates images from text prompts
+
+## Requirements
+
+- CUDA-capable GPU (24GB VRAM recommended)
+- PyTorch with CUDA support
+- flash-attn package
+
+## License
+
+See LICENSE file for details.
+
diff --git a/README_cn.md b/README_cn.md
new file mode 100644
index 0000000..d1a6377
--- /dev/null
+++ b/README_cn.md
@@ -0,0 +1,54 @@
+# ComfyUI_RH_mammothmoda
+
+ComfyUI 自定义节点，用于 MammothModa2 文本生成图像。
+
+## 功能特点
+
+- **文本生成图像**：使用 MammothModa2 进行高质量图像合成
+- **性能优化**：支持 INT8 量化实现高效推理
+- **Flash Attention**：使用 flash_attention_2 加速
+
+## 安装方法
+
+### 通过 ComfyUI Manager 安装（推荐）
+在 ComfyUI Manager 中搜索 "RunningHub Mammothmoda" 并安装。
+
+### 手动安装
+```bash
+cd ComfyUI/custom_nodes
+git clone https://github.com/HM-RunningHub/ComfyUI_RH_mammothmoda.git
+cd ComfyUI_RH_mammothmoda
+pip install -r requirements.txt
+```
+
+## 模型下载
+
+下载 MammothModa2-Preview 模型并放置到：
+```
+ComfyUI/models/MammothModa2-Preview/
+```
+
+模型来源：请查看 MammothModa2 官方仓库获取模型权重。
+
+## 使用说明
+
+1. **加载模型**：使用 "RunningHub Mammothmoda Loader" 节点
+2. **生成图像**：连接到 "RunningHub Mammothmoda T2I Sampler" 节点
+3. **配置参数**：设置提示词、尺寸（宽度/高度）、步数和引导比例
+4. **运行**：执行工作流生成图像
+
+## 节点说明
+
+- **RunningHub Mammothmoda Loader**：加载 MammothModa2 模型
+- **RunningHub Mammothmoda T2I Sampler**：从文本提示词生成图像
+
+## 系统要求
+
+- 支持 CUDA 的 GPU（推荐 24GB 显存）
+- PyTorch（支持 CUDA）
+- flash-attn 包
+
+## 许可证
+
+详见 LICENSE 文件。
+
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..ac76c68
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,8 @@
+torch>=2.0.0
+transformers>=4.40.0
+optimum-quanto
+qwen-vl-utils
+flash-attn>=2.0.0
+pillow
+numpy
+