About

The "cold start" problem is making it difficult for early-stage AI startups to enter the market. What is it, and why is it an issue?

Writing prompts for generative AI models, such as Stable Diffusion or Midjourney, can be challenging, especially if you want to generate high-quality images. For beginners, this can often be a source of frustration. We are bombarded with amazing images all over the internet, but when you try it yourself, the results are just... really bad.

We've made a lot of headway on the Visoid application in the last couple of weeks. Sign-ups for new users was opened up for everyone and it really made a big difference. In two weeks we've reached 85 users that have tested the application. We see that interaction is increasing as we add new functionality. In the beginning we were seeing users only run a render between 1-5 times, while now they're running 10+ renders.

You can now subscribe with your email to get notifications when the author posts a new article. Test it out below 👇

If you're looking for a quick and easy way to program a multistep ControlNet model using Python, you've come to the right place! Using the Huggingface Diffusers library, this is fairly easy to do. Let me show you how.