Model techniques map
Techniquesother

implementation detail · filed under other

Prompt Modality Ordering

Place image content before text and audio content after text in multimodal prompts.

Also called Modality order.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

For optimal performance with multimodal inputs, place: Image content before the text in your prompt. Audio content after the text in your prompt.

usedinference servingin Gemma 4Google DeepMind

Filed alongside

Other methods under other.