I'm the author of t2x and shrugginface.com, I'm surprised to see this landed on HN a month after I first shared it.
I originally planned to make it real during the holiday break but got distracted by other projects. This is the inspiration bump I needed, so I'll get back to shipping over the coming weeks
Simon's LLM tool is probably the best of any of these sorts of things! So thank you for making it, I still use it regularly to kick the tires on new models, and it served as a significant inspiration for the design of t2x.
The idea behind t2x was to make a stripped-down cli with a "functionality first" mindset and remove the actual selection of specific models from the user's flow.
If you run `ls -la | t2x "sort these files alphabetically"`, it will do the right thing.
However, subcommand like `t2x ask` are used to route you to a different model with different behavior. The ask subcommand currently makes requests to perplexity, where you can ask questions and get near realtime grounding from the world.
I'm curious, what specifically you're interested in from openrouter? Do they offer specific LLMs, or is it just a great way to kick the tires on new models as they emerge?
The original intention behind t2x was to be "functionality first", and make an opinionated call on which LLMs get used for specific functionality. However I think the way to go will be sane defaults and then allow user-specified models from something like openrouter.
Mostly because I thought of it more as an art project than a technical accuracy project. However, the honest answer to your question, is because I have a ridiculous amount of photos of my dog on my phone . Getting training data is hard work.
But this is totally true, I found that maybe 30% of the images I generated did not look like my dog at all. However the rest do a good job at capturing his eyes and facial expressions that he actually makes. I thought that the chosen image I worked from captured the look of his eyes super well.
But yeah, nobody but me would really appreciate that.
Yeah, it was likely just user error. I actually really love Draw Things, because I can run it locally on my mac and quickly experiment without having to sling HTTP requests or spin up GPUs.
I did the actual work back on March 11th, so I was likely on an older build; but I was seeing issues where inpainting was just replacing my selection/mask with a white background. I had the inpainting model loaded, but couldn't figure it out.
I'm planning to continue playing with Draw Things locally, and exploring the inpainting stuff. For such an iterative process I feel like a local client would make for the best experience.
I've trained a few smaller models using their Dreambooth notebook, but I think for 4000 training steps, an A100 will usually take 30-40min. I believe replicate also uses A100s for their dreambooth training jobs.
I’m excited to play with their memory stuff. I’m curious if they will add any hooks for allowing skills to store things intentionally.
The system skill idea is a little different in that you can store and query structured data out of your own SQLite db.