whosawhatsis

Results 48 comments of whosawhatsis

I'm planning an update that will require modifying most of the code in that section. Adding the duplicate parts probably would have happened anyway, but I'll keep the thing about...

The end_height variable should be at least the length of the motor body plus ~3mm for the mounting. I'll add a comment to explain this.

BTW, this also goes for internal overhangs, which should be bridging from the perimeter to the first pillar of infill material it intersects (or to the opposite perimeter, in the...

The system where fillets and chamfers need to be selected manually really makes it impossible to use them with programmatically-generated models. If I had an element in my model with...

Using the coreml code running on the GPU of an M1 Pro/Max with lots of RAM seems to be a small but nice improvement on speed. The big improvements, though,...

Pinch-to-zoom would be a welcome addition too, both on tablets and on other devices that support it, like apple's trackpads. I actually sometimes wish I could turn off scroll-to-zoom entirely,...

The most recent versions of stable diffusion seem to have implemented saving the prompt in the PNG metadata. It's working for me with https://github.com/invoke-ai/InvokeAI, so making it work in diffusionbee...

I've been doing a lot of testing with Apple's repo. Here are the modes that worked best on my M1 Max with 24-core gpu and 32GB: Using `--attention-implementation ORIGINAL` with...

Btw, one of the best uses for this, in my opinion, would be taking dreambooth models and applying them to different base models (sort of like the github rebase option)....