Skip to main content
Reference images work well for photographic qualities and broad aesthetics. They average out when you try to capture a really specific subject or visual language. When that happens, train a LoRA. Time: 8 minutes (plus a few minutes for training to complete) You’ll need: 10-30 reference images with a consistent style or subject, and a Hobby or Pro subscription
For the underlying concepts, see Custom LoRA models.

Train a LoRA on the dashboard

LoRAs are trained from the dashboard rather than from a workflow.

​
When to reach for a LoRA

A LoRA is a small adapter trained on your images. Once trained, every generation is biased toward that look without you having to prompt for it. Use a LoRA when reference images alone aren’t enough:
  • An artist’s style: Hansmeyer’s subdivision work, a specific architect’s tectonic language
  • Your studio’s aesthetic: accumulated visual identity across past projects
  • A unique architectural vocabulary: fenestration patterns, ornamentation, material syntax
For comparison: ControlNets enforce structure (depth maps, edges); IP-Adapters condition on a reference image without training. Different problems. For aesthetic capture, LoRA is the right tool.

​
1. Collect 10-30 training images

The images should all share either:
  • A consistent style (illustration, photographic look, line drawing)
  • Or a consistent subject (a specific person, a specific object)
Don’t mix. The LoRA learns the common element across all images, so consistency is what makes it work. Crop to the part you want captured. Strip out distracting backgrounds where you can.

​
2. Start a training run

There are two ways: From the canvas (fastest if you’ve already gathered images in a workflow):
  1. Paste or drop your training images onto the canvas
  2. Select all of them
  3. Open the menu → Training
  4. Click Train LoRA: the dashboard opens with the images pre-loaded
From the dashboard:
  1. Visit runchat.com/dashboard/training
  2. Click Train LoRA
  3. Upload images directly

​
3. Configure the training

In the training dialog:
  • Style or Subject: match what your training images share
  • Model: Flux is the default base. Flux Kontext is also an option.
  • Trigger word: a unique word you’ll add to prompts to activate the LoRA. Default is runchat. Make it something distinctive (avoid common words).
  • Description: a label so you can find this LoRA later
Click Start Training. Costs around 5,000 credits (~$5) and takes a few minutes.

​
4. Apply the LoRA in a workflow

Once training finishes:
  1. Refresh your browser to load the new LoRA into your profile
  2. In a workflow, add a Create node and switch the model to Flux LoRA
  3. In the node settings bar, click the LoRA dropdown (defaults to “No LoRA”)
  4. Pick your trained LoRA from the list
  5. Include your trigger word somewhere in the prompt
  6. Run
The output should reflect your training style.

​
5. Tune the strength

If the result is too close to the input image (LoRA influence is too weak) or too far (LoRA is overpowering), adjust the strength parameter in the settings bar:
  • Higher strength (e.g. 0.9), applies the LoRA more aggressively, pushes further from the input
  • Lower strength (e.g. 0.7), keeps the LoRA’s influence subtle and stays closer to the input
Guidance and inference steps are the other parameters worth experimenting with. Duplicate your node with alt-drag and test values side by side.

​
Why this matters

Once you have a LoRA for your studio’s aesthetic, every render you produce can be biased toward that look without writing increasingly long reference-heavy prompts. It’s the difference between describing a style every time and showing the model enough examples that it learns the style itself.

​
Next steps