-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
From what I've gathered by being involved early in the beta / in other discords, Midjourney was originally based on a fine-tuned version of classifier-free guided v-diffusion. The fine-tuning dataset was a manually curated set largely from LAION-2B similar to the laion-art / laion-hd. To make it so fast they were using Progressive Distillation (possibly distilling on PLMS steps rather than p/ddim?) and settings optimized to let them skip a few of the first steps like Quick CLIP-Guided Diffusion. There's a good chance they were doing some prompt augmentation as well, although I think this would be susceptible to prompt discovery attacks which I haven't seen any examples of for Midjourney.
Related posts
-
Show HN: Hacker News over SSH – Browse HN Articles Directly from Your Terminal
-
Ask HN: How do you develop and maintain a good note-taking habit?
-
Rabbit R1 can be run on a Android device
-
Flags Are Not Languages
-
Download your Learn course content with this free and open-source tool. All you need is a working computer and basic Python knowledge, and you can save a local copy of your Learn courses' content for future reference after the end of the term.