Glossary
Prompt
Also known as: AI prompt, text prompt, generation prompt
The text instruction given to an AI model that describes what to generate. For image and video models, prompts mix subject description, style direction, camera or composition hints, and optional negative prompts.
In depth
What it means in practice
A well-formed prompt for an image or video model specifies subject, style, composition, lighting, and (optionally) what to avoid. Strong prompts read more like a director's shot list than a sentence. "A young woman, golden hour rim light, 85mm portrait, soft windswept hair, urban bokeh background" is more controllable than "pretty photo of a woman".
Different models respond to different prompt styles. Sora 2 and Veo 3.1 respect explicit camera-move vocabulary ("slow push-in", "rack focus"). Kling responds well to reference-image conditioning. Nano Banana 2 handles in-image text reliably. The {Templates} section on hilens has ~40 open-source prompt examples drawn from CC BY 4.0 community libraries.
Example on hilens
Browse 40+ open-source prompts at /templates. Each one shows recommended models and credit cost on hilens.
Related
Negative prompt
Text describing what should not appear in the generated image or video. Used to suppress common failure modes like extra fingers, watermarks, blurry textures, or specific styles you want to avoid.
Reference image
An image uploaded alongside the prompt to condition the generation. The model preserves visual properties — composition, color palette, subject likeness, framing — from the reference in the output.
Aspect ratio
The width-to-height ratio of a generated image or video. Common ratios: 1:1 (square), 9:16 (vertical / TikTok / Reels), 16:9 (horizontal / YouTube), 4:5 (Instagram portrait), 3:4 (editorial vertical).