How to Run Image Diffusion Models Locally with Unsloth

Generate and edit AI images on your own computer using diffusion models without writing code or setting up a complex workflow. With Unsloth, you can run models like MiniMax-H3, Z-Image and FLUX locally with support for GGUFs, FP8, LoRAs, reference images, and more. Start with a text prompt or an existing image, then create, transform, edit, extend, upscale, or fine-tune images using the tools and workflows supported by each model.

Choose from MiniMax-H3, Z-Image, LTX, Qwen-Image, FLUX, SDXL and more.

To create your own LoRA, fine-tune a supported model on your dataset. See Fine-tune an image model to learn more.

⚡ Quickstart

1

Install or update

The desktop app is the easiest way to get started.

Download Unsloth Desktop

Follow the installer, then open the app from your applications. If you already have it installed, make sure it is up to date before continuing.

Command line

Prefer the terminal? Run the command for your operating system. The same command will update an existing installation.

MacOS, Linux, WSL:

curl -fsSL https://unsloth.ai/install.sh | sh

Windows PowerShell:

irm https://unsloth.ai/install.ps1 | iex

Launch Unsloth

Once the installation finishes, launch Unsloth:

unsloth studio -H 0.0.0.0 -p 8888

Open http://localhost:8888 if it does not open automatically.

2

Open Images

Select Images from the sidebar. The Create workflow opens by default.

Now we are ready to move onto the next step.

3

Choose a model

Open Select image model and choose a model from the selector.

The Recommended tab is a good place to start. For GGUF models, the best size for your device is also marked recommended. Sizes that may run slowly or not fit are marked TIGHT or OOM.

4

Enter a prompt

Describe the image you want to generate.

For example:

Top-down shot of a tranquil koi pond in a Japanese garden, orange, white and black koi swimming beneath the clear water, surrounded by moss-covered stepping stones and small wooden bridges, with red maple leaves floating on the surface. Bright midday light, saturated colour, crisp reflections. Whimsical cartoon illustration, 50mm.

You can keep the recommended settings for your first image.

5

Generate your first image

Select Generate. The first generation may take longer while the model downloads and loads.

Your result will appear in the gallery, where you can view its settings or download it.

⭐ Features

The available workflows depend on the model you load. Unsupported workflows are hidden automatically.

Create and edit images

• Create: Generate an image from a text prompt.

• Transform: Use an existing image as the starting point for a new generation.

• Inpaint: Select and regenerate part of an image.

• Extend: Generate content beyond the original canvas.

• Upscale: Increase the resolution of an image.

• Reference: Guide a generation with one or more reference images.

• Edit: Describe the changes you want to make to an image.

Edit requires a compatible model such as Qwen-Image-Edit or FLUX.1 Kontext.

LoRAs and ControlNet

Load compatible LoRAs to add a character, subject or visual style to your generations. Adjust the LoRA weight to control how strongly it affects the result.

Supported models can also use ControlNet to guide the structure of an image. Adjust its strength to control how closely the result follows the guidance image.

Gallery

Generated images are saved to the local gallery. Open a result to view its prompt and settings, select Recipe to restore its generation setup or download the image.

Supported models and workflows

What you want to do	Models to start with
Generate or transform images	Z-Image, Qwen-Image, FLUX.1, SDXL
Edit using instructions	Qwen-Image-Edit, FLUX.1 Kontext
Use reference images	FLUX.2 klein

More models are available in the model picker. Formats and workflows vary by model, and unsupported workflows are hidden automatically.

Generation settings

The default settings are a good starting point. However, it is possible to adjust settings to get the best result, these are the main parameters you may want to change:

Setting	What it changes
Prompt	Describes the image you want to create. In Edit, this becomes the instruction to follow.
Aspect ratio and resolution	Set the shape and size of the image. Larger images use more memory and take longer.
Steps	Control how long the model spends generating. More steps do not always improve the result.
Guidance	Controls how strongly the prompt guides the result. Some models work best at 0.
Seed	Helps recreate a result. Leave it empty to use a random seed.

Advanced generation settings

These controls change how the model runs on your device. Adjust them to reduce memory usage, improve performance or troubleshoot generation.

Setting	What it changes
Speed	Controls compilation and performance optimizations. Compiled modes may take longer during the first generation.
Precision	Changes the numerical format used to run the model. Lower precision can reduce memory usage. Available options depend on the model and hardware.
Attention	Selects the attention implementation used during generation.
Memory	Balances generation speed against GPU memory usage. Try Low VRAM if a model is close to your memory limit.
Step cache	Reuses some calculations between diffusion steps to improve generation speed.
CPU offload	Moves parts of the model into system memory. This reduces GPU memory usage but may make generation slower.

⚠️ Troubleshooting

Images does not appear

Update to the latest version, then restart the app. See Updating Unsloth for instructions.

A model will not download or load

Some image models are large and take time to download. Check that you have enough free storage and a stable internet connection.

Some models also require you to accept their licence on Hugging Face and add a Hugging Face token before downloading them.

The model runs out of memory

Try a smaller GGUF quantization or a 4-bit version of the model. For GGUF models, start with the size marked recommended.

You can also:

• Lower the image resolution.

• Keep the batch size at 1.

• Close other applications using the GPU.

• Choose a smaller model.

A TIGHT model may use system memory and run more slowly. A model marked OOM is unlikely to fit.

A workflow is missing

The available workflows depend on the loaded model. Unsupported workflows will not appear.

For example, instruction-based editing requires a model such as Qwen-Image-Edit or FLUX.1 Kontext.

❓ FAQ

Does image generation run locally?

Yes. Once a model is downloaded, image generation runs on your device.

What is the difference between Transform and Edit?

Transform redraws an existing image using a prompt that describes the complete result.

Edit follows instructions such as changing a background or adding an object. It requires a compatible editing model.

Can I train my own image LoRA?

Yes. Fine-tune a supported model on your own images, then load the finished LoRA in Create.

See Fine-tune an image model to learn more.