CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2205.15868/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTCogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers — mentioned by nodjahttps://news.ycombinator.com/item?id=32820267urn:hackerpapers:mention:2205.15868:32820267Tue, 13 Sep 2022 03:09:25 GMT<p>Depending on how you&#x27;re measuring it, video generation will come in less than 12 months, or it&#x27;s already here. - In the Video Diffusion paper[1] they generate 64x64 16 frame videos, model is not released, but an open source implementation using an imagen-like pipeline exists[2], no model is available publicly. - The CogVideo paper[3], which is essentially a huge transformer model, can generate 480x480 videos, the code for the paper and models are open source[4], but be warned that you need a huge GPU like an A100 to run the damned thing. The future of text to video generation will probably be…</p><p><a href="https://hackerpaper.kaipfister.de/p/2205.15868/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV