About
A library of AI prompts, hand-picked daily.
OPWAN.AI aggregates the most striking AI image and video generation prompts shared on X. Every day we fetch new posts, classify them by model, and surface the highest-signal work so you don’t have to scroll for it.
How it works
- Prompts are fetched from public X posts via TwitterAPI.io.
- Each post is classified by image / video model (Seedance 2.0, GPT-Image-2, Nano Banana 2, and more).
- We label the prompt source as Original, AI inferred, or No prompt — so you always know where the text came from.
- Media is cached on Cloudflare R2 with credit linked back to the original author.
Why three source labels
Not every great image on X comes with the prompt that produced it. Rather than guess quietly, we tag every entry as one of three honest states so you know what you’re looking at:
- Original — the author shared the prompt themselves; we copy it verbatim.
- AI inferred — no original prompt was published, but our model wrote a plausible reconstruction. Use as a starting point, not a guarantee.
- No prompt— the post is interesting but we don’t have any prompt text. Click through to the source if you want to ask the author.
Credit & licensing
All prompts and media credit the original author with a link back to the source post on X. OPWAN.AI does not claim ownership of any aggregated content. We respect the original author’s rights — if you are an author and want a post removed, email hello@opwan.ai and we’ll take it down within 24 hours.
What you can do here
- Browse the full feed at /, sorted by heat / recent / quality.
- Filter by model: Seedance 2.0, GPT-Image-2, and others.
- Save prompts to your local bookmarks at /saved (no account needed).
- Export any model’s feed as Markdown / JSON / CSV from the model page.
- Share any prompt URL — they’re permanent.