Question 1

How many images should I provide?

Accepted Answer

At least 10 — more is usually better, up to about 50. For a subject, prioritise variety in pose and lighting. For a style, prioritise consistency in aesthetic.

Question 2

Do I need captions?

Accepted Answer

No, captions are optional. If you do include them, name each `.txt` file identically to its image and use `[trigger]` wherever you want the trigger phrase injected.

Question 3

How long does training take?

Accepted Answer

Typically 5-10 minutes from submission to a downloadable `.safetensors` file. The endpoint is asynchronous — provide a `webhook_url` or poll the status endpoint.

Question 4

What is the trigger phrase for?

Accepted Answer

It is the unique token you mention in inference prompts to activate the trained concept. Pick something short and unusual so it does not collide with normal vocabulary in your prompts.

Question 5

Where can I use the trained LoRA?

Accepted Answer

Any image-generation endpoint that accepts a Flux Dev LoRA URL — including muapiapp's flux-dev-lora — can consume the resulting `.safetensors` file directly.