Hacker News Reader

Comment by ChaitanyaSai | Hacker News Reader

We've been experimenting with SD and results are quite underwhelming. DALLE2 seems a lot more usable. Any reason why most are sticking with SD? (If that assumption is true)

View on HN

StableDiffusion produces better pictures once you get what you want. Dall.e2 is very good at understanding your prompt but the images are not very detailed when you look closely. They are full of artefacts, and the faces are zombi like unless they fill the whole frame.

But you can use stable diffusion and dall.e together. Or use MidJourney v4 which is simply the best right now.

How does MidJourney v4 do illustrations. The early versions we saw seemed a little too artistic and also had this distinct "looks like midjourney" signature. Any links you can point me to? Thanks!

I haven’t found a good explanation of how mid journey works in detail. Many people guess that they are not collecting the data for no reasons, and that the model is fine tuned using data and user ratings from the previous generations.

Openness for me. Stable diffusion runs on a machine that sits 5 feet away from me and delivers good quality results in under 3 seconds per image. I don't have to shy away from politically (or otherwise) questionable prompts, or in the case of business applications, potentially leaking sensitive data, because I know that they aren't being recorded forever on a remote server somewhere. I can also tinker with the code, which has helped me add a bunch of features that really synergize with my workflow.

As others have noted, getting good results from SD is very much a numbers and parameters game. I've witnessed first hand how some people get frustrated easily and quit tinkering because their initial approaches don't work right away. Prompt and parameter engineering really is a skill that you have to grow, and it makes a world of difference. img2img is also much finickier than text2img.

Reply on news.ycombinator.com