InfraLens

LoRA Injection Reading

This starter is annotated reading material and the source of truth for the lab preview. Running anything is optional; the reading goal is to explain the mechanism without hiding behind a framework call.

Reading focus

Read LoRA as a small trainable delta on selected weight matrices.

Annotated sketch

## LoRA mental model

```text
output = x @ base_weight
adapter_delta = scale * (x @ A @ B)
output = output + adapter_delta

Read the adapter as a small learned correction to an existing layer. ```

What to explain

• base_weight remains the pretrained matrix.
• A and B form a low-rank update.
• scale controls how strongly the adapter changes the layer.

Common trap

• LoRA is not a new scheduler.
• LoRA is not the same mechanism as ControlNet.

This site is open source. Improve this page.