Meet HunyuanImage-3.0, an advancement beyond the usual tradeoffs of text-to-image systems. Built as a native unified multimodal model inside an autoregressive framework, it no longer treats vision and language as weirdly stitched components but as one coherent generation engine, which yields images that are both semantically faithful and compositionally sophisticated. Under the hood it’s the largest open-source image-generation Mixture-of-Experts to date: 64 experts, ~80 billion parameters total, with roughly 13 billion parameters activated per token, a capacity design that gives the model both breadth of world knowledge and the focused horsepower to render fine visual detail. Extensive dataset curation plus reinforcement-learning post-training sharpen its prompt adherence and aesthetic output, so you get photorealistic, high-fidelity images that honor nuance (lighting, texture, and small object relationships) while avoiding common alignment failures. Crucially, the unified architecture also improves reasoning: HunyuanImage-3.0 can intelligently expand sparse or underspecified prompts using its world knowledge, filling in contextually appropriate details so outputs feel complete and intentional rather than half-baked. For creators, researchers, and engineers who care about semantic accuracy, visual quality, and reliable prompt behavior, this model offers a compelling combination of scale, architecture, and training polish that’s worth trying.
Ready to try it? Below you’ll find a quick, hands-on installation and inference walkthrough that gets HunyuanImage-3.0 up and running, fast, reproducible, and practical for experiments or production prototypes.
Prerequisites
The minimum system requirements for running this model are:
Step-by-step process to install and run HunyuanImage-3.0
For the purpose of this tutorial, we’ll use a GPU-powered Virtual Machine by NodeShift since it provides high compute Virtual Machines at a very affordable cost on a scale that meets GDPR, SOC2, and ISO27001 requirements. Also, it offers an intuitive and user-friendly interface, making it easier for beginners to get started with Cloud deployments. However, feel free to use any cloud provider of your choice and follow the same steps for the rest of the tutorial.
Step 1: Setting up a NodeShift Account
Visit app.nodeshift.com and create an account by filling in basic details, or continue signing up with your Google/GitHub account.
If you already have an account, login straight to your dashboard.
Step 2: Create a GPU Node
After accessing your account, you should see a dashboard (see image), now:
- Navigate to the menu on the left side.
- Click on the GPU Nodes option.
- Click on Start to start creating your very first GPU node.
These GPU nodes are GPU-powered virtual machines by NodeShift. These nodes are highly customizable and let you control different environmental configurations for GPUs ranging from H100s to A100s, CPUs, RAM, and storage, according to your needs.
Step 3: Selecting configuration for GPU (model, region, storage)
- For this tutorial, we’ll be using 1x H200 GPU, however, you can choose any GPU as per the prerequisites.
- Similarly, we’ll opt for 200GB storage by sliding the bar. You can also select the region where you want your GPU to reside from the available ones.
Step 4: Choose GPU Configuration and Authentication method
- After selecting your required configuration options, you’ll see the available GPU nodes in your region and according to (or very close to) your configuration. In our case, we’ll choose a 4x H100 80GB GPU node with 96 vCPUs/882 GB RAM/300GB SSD.
2. Next, you’ll need to select an authentication method. Two methods are available: Password and SSH Key. We recommend using SSH keys, as they are a more secure option. To create one, head over to our official documentation.
Step 5: Choose an Image
The final step is to choose an image for the VM, which in our case is Nvidia Cuda.
In our previous blogs, we used pre-built images from the Templates tab when creating a Virtual Machine. However, for running a CUDA dependent model like HunyuanImage-2.1, we need a latest CUDA version like CUDA12.4. Therefore, in this case, we switched to the Custom Image tab and selected a specific Docker image that meets all runtime and compatibility requirements.
We chose the following image:
nvidia/cuda:12.8.0-devel-ubuntu24.04
This image is essential because it includes:
- Full CUDA toolkit (including
nvcc)
- Proper support for building and running GPU-based applications
- Compatibility with CUDA 12.4.0 required by model operations
Launch Mode
We selected:
Interactive shell server
This gives us SSH access and full control over terminal operations — perfect for installing dependencies, running benchmarks, and launching models.
Docker Repository Authentication
We left all fields empty here.
Since the Docker image is publicly available on Docker Hub, no login credentials are required.
Identification
nvidia/cuda:12.8.0-devel-ubuntu24.04
That’s it! You are now ready to deploy the node. Finalize the configuration summary, and if it looks good, click Create to deploy the node.
Step 6: Connect to active Compute Node using SSH
- As soon as you create the node, it will be deployed in a few seconds or a minute. Once deployed, you will see a status Running in green, meaning that our Compute node is ready to use!
- Once your GPU shows this status, navigate to the three dots on the right, click on Connect with SSH, and copy the SSH details that appear.
As you copy the details, follow the below steps to connect to the running GPU VM via SSH:
- Open your terminal, paste the SSH command, and run it.
2. In some cases, your terminal may take your consent before connecting. Enter ‘yes’.
3. A prompt will request a password. Type the SSH password, and you should be connected.
Output:
Next, If you want to check the GPU details, run the following command in the terminal:
!nvidia-smi
Step 7: Set up the project environment with dependencies
- Create a virtual environment using Anaconda.
conda create -n hunyuan python=3.12 -y && conda activate hunyuan
Output:
2. Install required dependencies.
pip install torch==2.7.1 torchvision==0.22.1 torchaudio==2.7.1 --index-url https://download.pytorch.org/whl/cu128
pip install -i https://mirrors.tencent.com/pypi/simple/ --upgrade tencentcloud-sdk-python
pip install einops>=0.8.0 numpy==1.26.4 pillow==11.3.0 diffusers>=0.32.0
pip install safetensors==0.4.5 tokenizers>=0.21.0 transformers[accelerate,tiktoken]>=4.56.0 huggingface_hub[cli]
pip install gradio>=4.21.0
pip install flash-attn==2.8.3 --no-build-isolation
pip install flashinfer-python
Output:
Step 8: Download and Run the model
1. Download model checkpoints with the following command.
hf download tencent/HunyuanImage-3.0 --local-dir ./HunyuanImage-3
Output:
2. Install and run jupyter notebook.
conda install -c conda-forge --override-channels notebook -y
conda install -c conda-forge --override-channels ipywidgets -y
jupyter notebook --allow-root
3. If you’re on a remote machine (e.g., NodeShift GPU), you’ll need to do SSH port forwarding in order to access the jupyter notebook session on your local browser.
Run the following command in your local terminal after replacing:
<YOUR_SERVER_PORT> with the PORT allotted to your remote server (For the NodeShift server – you can find it in the deployed GPU details on the dashboard).
<PATH_TO_SSH_KEY> with the path to the location where your SSH key is stored.
<YOUR_SERVER_IP> with the IP address of your remote server.
ssh -L 8888:localhost:8888 -p <YOUR_SERVER_PORT> -i <PATH_TO_SSH_KEY> root@<YOUR_SERVER_IP>
Output:
After this copy the URL you received in your remote server:
And paste this on your local browser to access the Jupyter Notebook session.
4. Run the model for inference by executing the following code in the Jupyter notebook cell with your desired prompt.
from transformers import AutoModelForCausalLM
# Load the model
model_id = "./HunyuanImage-3"
# Currently we can not load the model using HF model_id `tencent/HunyuanImage-3.0` directly
# due to the dot in the name.
kwargs = dict(
attn_implementation="flash_attention_2", # Use "sdpa" if FlashAttention isn't installed
trust_remote_code=True,
torch_dtype="auto",
device_map="auto",
moe_impl="flashinfer", # Use "eager" if FlashInfer isn't installed
)
model = AutoModelForCausalLM.from_pretrained(model_id, **kwargs)
model.load_tokenizer(model_id)
# generate the image
prompt = "A brown and white dog is running on the grass"
image = model.generate_image(prompt=prompt, stream=True)
image.save("image.png")
Output:
Here’s the final generated image:
Conclusion
HunyuanImage-3.0 sets a new standard in open-source multimodal generation with its unified autoregressive architecture, massive 80B-parameter Mixture-of-Experts design, and advanced reinforcement learning fine-tuning that together deliver unmatched semantic precision, visual fidelity, and intelligent prompt reasoning. But unlocking the full potential of such a large-scale model requires infrastructure that’s equally powerful and flexible, and that’s where NodeShift Cloud comes in. By offering decentralized, on-demand GPU resources at scale, NodeShift ensures that researchers, creators, and businesses can experiment, deploy, and scale HunyuanImage-3.0 seamlessly, without the overhead of maintaining costly hardware. The combination of cutting-edge model capabilities and NodeShift’s cloud-native infrastructure empowers users to explore next-level AI creativity with accessibility, efficiency, and reliability.
