Skip to content
Prompt library

PROMPTS

1346 original and curated AI prompts across image, video, music, and tutorials. Browse by tool, use case, and difficulty; each entry shows its available notes and examples.

Filters3 activeExpand
PRO01
IMAGEIdeogram 3.0
2026-07-10

Livestream Three-Screen Set: Countdown, Be Right Back, and Outro in One Visual Style

Generate three OBS stream scenes in one go — starting-soon countdown, be-right-back, and stream-ending outro — sharing the same layout and color scheme with only the status text changing, with space reserved for the webcam and chat overlay, so your channel has one consistent brand look from stream start to sign-off.

AdvancedGen in-site
Read

Free02
IMAGEIdeogram 3.0
2026-06-15

Small-Business Logo + Icon Set: One Prompt for a Usable Brand Mark Draft

Ideogram 3.0's Design mode generates a clean, flat brand logo (Chinese and English side by side) plus a matching set of 6-8 icons in the same style, giving you a complete visual identity before opening a shop or taking on a client.

BeginnerGen in-site
Read

Free03
IMAGEIdeogram 3.0
2026-04-24

Logo Wordmark Draft

A pure text wordmark logo for a brand — Ideogram handles letter spacing and font weight far better than Midjourney. Good for exploring initial directions and quickly aligning on style with a designer.

BeginnerGen in-site
Read

PRO04
IMAGEIdeogram 3.0
2026-04-24

Product Packaging Key Visual · Front

Front packaging for food, skincare, and curated retail products — Ideogram renders product names, ingredients, and certification text on packaging 10x more reliably than other models.

IntermediateGen in-site
Read

Free05
IMAGEIdeogram 3.0
2026-04-24

Billboard Ad · Text-Hero

Outdoor billboards / subway ads / pop-up backdrops — text needs to stay readable from 10 meters away. A minimal composition with extra-large type is the only solution.

IntermediateGen in-site
Read

Free06
IMAGEIdeogram 3.0
2026-04-22

Ideogram 3.0 text-rendered logos: clean type in both Chinese and English

Ideogram 3.0's text-in-image is the most accurate of any current image model. Not just English, it renders Chinese, Japanese, and Korean precisely too, ready to use for logos, signage, and book covers.

BeginnerGen in-site
Read