You cant I think because there using wombo.ai and wombo.ai is shutdown FOREVER. Source: 11 months ago

I've been watching Unstable Diffusion since day 1, and I still remember to this day how on every single announcement they linked their patreon with the caption "donate to us so we can keep supporting the development of open source AI!". Oh yes, surely unstable is in need, it's not like that wombo.ai colab and 1,000$ gpu grant is gonna be enough. Source: about 1 year ago

Shit looks like that wombo.ai stuff. Source: over 1 year ago

Seriously. When it started,wombo.ai and stuff was funni. But now with millions of AI's such as different dimension me,Dall-E mini,etc,it's became stale. Source: over 1 year ago

The new flair is intended for works generated by 'AI' -- ie a neural network that was trained on a dataset (usually visual) that was fed a prompt to create a work. This includes video works like deepfake-like videos like wombo.ai works or fanworks using the lensa dataset (or whatever dataset). Even if you have trained a neural network on your own dataset of your own images that you created yourself please use... Source: over 1 year ago

Sad, I had a lot of fun with it making StackRoboflow[1] (This Question Does Not Exist) a few years ago. The models (AWD-LSTM and GPT-2) weren't good enough back then to usefully answer programming questions -- but it's super cool to see that vision realized with GPT-4 and other modern LLMs. [1] https://stackroboflow.com. - Source: Hacker News / 12 months ago

This feels like a Stack Roboflow question, however it's also what a lot of people on SO are actually like. "I don't want to read documentation and learn, I want a code answer!". Source: over 1 year ago