B-TIER demo
Runway Gen-3 — hands-on first test of public text-to-video
100k ft — What is this?
Runway Gen-3 — hands-on first test of public text-to-video
50k ft — Why care?
A quick paid-tier test of Runway Gen-3 Alpha right after public release: a hyper-real macro prompt (miniature horned puppies on a fingertip, then butterfly wings) took a few generations to land. Mostly a first-impressions reaction, not a workflow.
10k ft — Key takeaways
• Gen-3 needs several generations per prompt; budget credits accordingly
• Macro/close-up subjects with one surreal detail are a reliable showcase prompt style
5k ft — Tools & techniques
Runway, Runway Gen-3, Sora
text-to-video prompting, video generation
1k ft — Deep-dive / try it
Runwayml gen-3 is out and the results are wild
Transcript excerpt
Forget about Sora, Runway ML just released Gen 3 to the public and the results are wild. This is arguably the best text to video right now that anybody can use. However, after seeing the videos I was still a little bit skeptical so I decided to check it out for myself to see whether it lived up to the hype. So I paid the $15 for the standard tier and typed in the prompt a hyper realistic close-up of two miniature puppies with horns on a fingertip and these were the results. It took a few generations and I then also changed the horns to butterfly wings and I can definitely say I was blown away by the results and the examples that I showed earlier are certainly achievable by anybody using this tool.