Instructions to use windecay/SimpleSDXL2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use windecay/SimpleSDXL2 with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf windecay/SimpleSDXL2:Q2_0 # Run inference directly in the terminal: llama cli -hf windecay/SimpleSDXL2:Q2_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf windecay/SimpleSDXL2:Q2_0 # Run inference directly in the terminal: llama cli -hf windecay/SimpleSDXL2:Q2_0
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf windecay/SimpleSDXL2:Q2_0 # Run inference directly in the terminal: ./llama-cli -hf windecay/SimpleSDXL2:Q2_0
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf windecay/SimpleSDXL2:Q2_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf windecay/SimpleSDXL2:Q2_0
Use Docker
docker model run hf.co/windecay/SimpleSDXL2:Q2_0
- LM Studio
- Jan
- Ollama
How to use windecay/SimpleSDXL2 with Ollama:
ollama run hf.co/windecay/SimpleSDXL2:Q2_0
- Unsloth Desktop
- Pi
How to use windecay/SimpleSDXL2 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf windecay/SimpleSDXL2:Q2_0
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "windecay/SimpleSDXL2:Q2_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use windecay/SimpleSDXL2 with Docker Model Runner:
docker model run hf.co/windecay/SimpleSDXL2:Q2_0
- Lemonade
How to use windecay/SimpleSDXL2 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull windecay/SimpleSDXL2:Q2_0
Run and chat with the model
lemonade run user.SimpleSDXL2-Q2_0
List all available models
lemonade list
- Hermes Agent
How to use windecay/SimpleSDXL2 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf windecay/SimpleSDXL2:Q2_0
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default windecay/SimpleSDXL2:Q2_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use windecay/SimpleSDXL2 with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf windecay/SimpleSDXL2:Q2_0
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "windecay/SimpleSDXL2:Q2_0" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Update update_history.txt
Browse files- update_history.txt +13 -32
update_history.txt
CHANGED
|
@@ -5,43 +5,24 @@
|
|
| 5 |
2025-0319 v1.32 资源分享网盘添加了50系显卡专用临时版本。优化了打开用户和模型目录、修改模型文件夹路径的操作确认逻辑。
|
| 6 |
|
| 7 |
0406测试主分支更新:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
2025-0415-
|
| 9 |
1,优化:base包从hf迁到国内地址,检测有更新再下载本地实施本地包升级,规避网络故障导致启动失败;
|
| 10 |
2,优化:代码仓更新改为强制同步,直接覆盖本地文件,规避本地代码仓故障导致更新失败;
|
| 11 |
3,新增:p2p模块新增固定端口配置项;
|
| 12 |
4,优化:一键转绘预置包升级。
|
| 13 |
2025-0409-瘦身了新的程序包,新程序包编号0406,由于改动大,若启动时出现Update Fail可以点击启动器选择分支按钮强制同步,仍然建议使用最新的0406版程序。
|
| 14 |
-
|
| 15 |
-
1,p2p模块的第一个应用,远程生图,即简单配置后节点A可用节点B的算力生图,无须外网ip和穿透工具;
|
| 16 |
-
2,配套新增启动参数,可无后端启动。这样无GPU卡设备启动后可远程调用其他节点的算力生图;
|
| 17 |
-
3,一键深度预置包(小河);
|
| 18 |
-
4,一键转绘预置包(冰华);
|
| 19 |
-
5,修复了Flux低显存黑图、不出图的问题。
|
| 20 |
-
2025-0401-
|
| 21 |
-
1,高级选项菜单继续优化调整,去掉高级tab,将关联出图的高级设置合并到“设置”栏里,进行分栏处理。
|
| 22 |
-
2,将原高级tab应用级的设置项合并到“我的”“应用设置”里。新增一些记忆最后设置的项。
|
| 23 |
-
3,恢复联系tab到顶部,添加simpai logo图片。
|
| 24 |
-
4,ipadpter目录可见controlnet目录模型
|
| 25 |
-
5,重绘加载图片自动反推
|
| 26 |
-
6,队列生图有步骤就不受总超时时长限制。
|
| 27 |
-
7,p2p远程生图流程已打通,将开启内部测试。
|
| 28 |
-
2025-0327-
|
| 29 |
-
1,为p2p模块的启用更新UI,将“服务”改成“我的”,身份管理置顶。预留“画廊”标签页。
|
| 30 |
-
2,“我的”标签页划分为“应用设置”/“本地系统”/“社区网络”/“联系我们”,对配置项进行重新归类。
|
| 31 |
-
3,应用设置里的切图回填提示词/翻译引擎的设置项做记忆处理,重启应用后默认退出前的设置。
|
| 32 |
-
4,取消admin配置的保存按钮,更改设置后自动记忆,重启后默认退出的前的设置。
|
| 33 |
-
5,社区网络新增p2p网络启用开关,并新增连接状态:Off/On/On-P2P。Off状态无上游节点连接,无法绑定新身份和非二维码绑定。On状态有上游连接,正常处理身份绑定。On-P2P状态表示连入专属P2P网络,具备远程分享能力。
|
| 34 |
-
6,修正图像输入开启后切换场景预置包的bug
|
| 35 |
-
7,新增预置包内置参考图目录
|
| 36 |
|
| 37 |
0406测试可视化分支更新:
|
| 38 |
-
2025-
|
| 39 |
-
2025-
|
| 40 |
-
2025-0413-修复了50系分支miniCPM,增加了默认风格界面右键发送提示词。
|
| 41 |
-
2025-0409-同步主分支0409更改
|
| 42 |
-
2025-0407-同步主分支0407内容
|
| 43 |
-
2025-0404-调整了模型加载界面,恢复原始样貌。下拉列表加入了模型悬浮窗。右键可以展开模型画廊。
|
| 44 |
-
2025-0401-升级可视化风格栏,左键点击为勾选风格,右键点击为把风格词发送到正、反向提示词输入栏。同步主分支0401更新。
|
| 45 |
-
2025-0327-同步主分支0327内容。
|
| 46 |
-
2025-0324-修复了一个通配符点击报错。现在空提示词不会进入历史提示词队列。
|
| 47 |
-
2025-0323-增加可视化风格悬浮文字栏,展示风格里实际包含的提示词。修复风格排序、翻译的事件链。
|
|
|
|
| 5 |
2025-0319 v1.32 资源分享网盘添加了50系显卡专用临时版本。优化了打开用户和模型目录、修改模型文件夹路径的操作确认逻辑。
|
| 6 |
|
| 7 |
0406测试主分支更新:
|
| 8 |
+
- [2025.04.22]更新内容:
|
| 9 |
+
(1)新增:在日志记录页面里增加视频生成的历史并可播放视频;
|
| 10 |
+
(2)修复:之前规格化生成参数时导致增强修图参数异常。
|
| 11 |
+
- [2025.04.21]更新内容:
|
| 12 |
+
(1)新增:comfyd的三方FramePackWapper,TeaCache,VideoHelperSuite节点;
|
| 13 |
+
(2)新增:自研的websocket_video_save节点,支持webm/mp4的vp9/av1/h264/h265编码;
|
| 14 |
+
(3)增强:生图流程支持视频生成和视频本地保存;
|
| 15 |
+
(4)增强:系统密钥自恢复机制,避免被环境干扰;
|
| 16 |
+
(5)修复:p2p远程调用并发丢包和指令乱序;
|
| 17 |
+
(6)修复:reserved_vram和wavespeed参数默认值丢失。
|
| 18 |
2025-0415-
|
| 19 |
1,优化:base包从hf迁到国内地址,检测有更新再下载本地实施本地包升级,规避网络故障导致启动失败;
|
| 20 |
2,优化:代码仓更新改为强制同步,直接覆盖本地文件,规避本地代码仓故障导致更新失败;
|
| 21 |
3,新增:p2p模块新增固定端口配置项;
|
| 22 |
4,优化:一键转绘预置包升级。
|
| 23 |
2025-0409-瘦身了新的程序包,新程序包编号0406,由于改动大,若启动时出现Update Fail可以点击启动器选择分支按钮强制同步,仍然建议使用最新的0406版程序。
|
| 24 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
0406测试可视化分支更新:
|
| 27 |
+
2025-0422同步了主分支0422版本
|
| 28 |
+
2025-0417添加了悬浮窗主动躲避鼠标
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|