Promptweet
120 prompts · 6 libraries

See the shot. Then copy what wrote it.

Every prompt lists the camera move, lighting and duration behind its clip, read from the text, not guessed. Filter by technique, not just by model.

120 prompts·6 libraries·26 categories·100% watchable

Latest from Seedance 2.5

Latest from Seedance 2.0

Latest from Grok Imagine

Latest from MiniMax H3

Latest from Veo 3

Latest from Kling

What this library says about writing a prompt

Four things hold across this set, each measured against the 120 prompts above rather than asserted.

Names the camera movee.g. tracking, orbit, push-in
96.7%
States a durationmost that do ask for 15s
100%
States an aspect ratioleast specified field
100%
Locks a consistency traitsubject, face or outfit held constant
64.2%

How the libraries compare

Same measurement, applied per model. A lower number means that model's writers leave more to the model, not that the prompts are worse.

LibraryPromptsNames cameraStates durationLocks consistency
Seedance 2.57594.7%100%69.3%
Seedance 2.022100%100%54.5%
Grok Imagine1100%100%100%
MiniMax H317100%100%58.8%
Veo 31100%100%0%
Kling4100%100%50%

About this library

Promptweet is a prompt library: real AI-video prompts pulled from posts on X, each paired with the actual clip it produced and a spec sheet read from its own text. Most clips here are real generations, linked back to their source post. A few library corners are still filling in and show placeholder content in the meantime, always marked as sample data. Browse by model, filter by camera move or lighting, open a prompt, copy it.