Instructions to use imikeliu/HunyuanImage-2.1-reprompt-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use imikeliu/HunyuanImage-2.1-reprompt-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="imikeliu/HunyuanImage-2.1-reprompt-gguf",
	filename="reprompt-F32.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use imikeliu/HunyuanImage-2.1-reprompt-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf imikeliu/HunyuanImage-2.1-reprompt-gguf:F32
# Run inference directly in the terminal:
llama-cli -hf imikeliu/HunyuanImage-2.1-reprompt-gguf:F32

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf imikeliu/HunyuanImage-2.1-reprompt-gguf:F32
# Run inference directly in the terminal:
llama-cli -hf imikeliu/HunyuanImage-2.1-reprompt-gguf:F32

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 imikeliu/HunyuanImage-2.1-reprompt-gguf:F32
# Run inference directly in the terminal:
./llama-cli -hf imikeliu/HunyuanImage-2.1-reprompt-gguf:F32

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 imikeliu/HunyuanImage-2.1-reprompt-gguf:F32
# Run inference directly in the terminal:
./build/bin/llama-cli -hf imikeliu/HunyuanImage-2.1-reprompt-gguf:F32

Use Docker

docker model run hf.co/imikeliu/HunyuanImage-2.1-reprompt-gguf:F32

LM Studio
Jan
Ollama
How to use imikeliu/HunyuanImage-2.1-reprompt-gguf with Ollama:
```
ollama run hf.co/imikeliu/HunyuanImage-2.1-reprompt-gguf:F32
```

Unsloth Studio

How to use imikeliu/HunyuanImage-2.1-reprompt-gguf with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for imikeliu/HunyuanImage-2.1-reprompt-gguf to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for imikeliu/HunyuanImage-2.1-reprompt-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for imikeliu/HunyuanImage-2.1-reprompt-gguf to start chatting

How to use imikeliu/HunyuanImage-2.1-reprompt-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf imikeliu/HunyuanImage-2.1-reprompt-gguf:F32

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "imikeliu/HunyuanImage-2.1-reprompt-gguf:F32"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use imikeliu/HunyuanImage-2.1-reprompt-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf imikeliu/HunyuanImage-2.1-reprompt-gguf:F32

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 imikeliu/HunyuanImage-2.1-reprompt-gguf:F32

Run Hermes

hermes

Docker Model Runner
How to use imikeliu/HunyuanImage-2.1-reprompt-gguf with Docker Model Runner:
```
docker model run hf.co/imikeliu/HunyuanImage-2.1-reprompt-gguf:F32
```

Lemonade

How to use imikeliu/HunyuanImage-2.1-reprompt-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull imikeliu/HunyuanImage-2.1-reprompt-gguf:F32

Run and chat with the model

lemonade run user.HunyuanImage-2.1-reprompt-gguf-F32

List all available models

lemonade list

A direct GGUF convertion of tencent/HunyuanImage-2.1 reprompt (Prompt Enhancement) model. Provided As-is.

由 tencent/HunyuanImage-2.1 的提示词增强模型直接转换的 GGUF 文件。按原样提供。

The prompt recommended by the study is as follows:

你是一位图像生成提示词撰写专家，请根据用户输入的提示词，改写生成新的提示词，改写后的提示词要求：1 改写后提示词包含的主体/动作/数量/风格/布局/关系/属性/文字等 必须和改写前的意图一致； 2 在宏观上遵循“总-分-总”的结构，确保信息的层次清晰；3 客观中立，避免主观臆断和情感评价；4 由主到次，始终先描述最重要的元素，再描述次要和背景元素；5 逻辑清晰，严格遵循空间逻辑或主次逻辑，使读者能在大脑中重建画面；6 结尾点题，必须用一句话总结图像的整体风格或类型。

建议的提示词如下：

你是一位图像生成提示词撰写专家，请根据用户输入的提示词，改写生成新的提示词，改写后的提示词要求：1 改写后提示词包含的主体/动作/数量/风格/布局/关系/属性/文字等 必须和改写前的意图一致； 2 在宏观上遵循“总-分-总”的结构，确保信息的层次清晰；3 客观中立，避免主观臆断和情感评价；4 由主到次，始终先描述最重要的元素，再描述次要和背景元素；5 逻辑清晰，严格遵循空间逻辑或主次逻辑，使读者能在大脑中重建画面；6 结尾点题，必须用一句话总结图像的整体风格或类型。

Downloads last month: 82

GGUF

Model size

8B params

Architecture

hunyuan-dense

Hardware compatibility

2-bit

4-bit

8-bit

32-bit

View +1 variant

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support