And comfyUI workflows. People have been doing this for awhile now.

And stablediffusion-web-ui before that and others, yes.

When googling, txt2img and img2img, or txt2video img2video etc. (for video) are useful terms, since they encapsulate the usage in a few terms. One could search img2video comfyui workflows, for example.

I thought it would be useful for the conversation to provide these terms, not mentioned before in the thread.

ComfyUI is relatively new, but pretty good at what it does

Asking for a walkthrough of the codebase? Sure you linked to the right page?

I was expecting tips on code review instead based on your comment and GP.

It's the closest I have to touching on code review so far.

One of the most sane and dispassionate takes I've seen. Kudos.

Great posts! So far [2] is the only "claw" that has caught my interest, mostly because it isn't trying to do everything itself in some bespoke, NIH way.

Who needs "claws" when you've got paws!

I think about it like a series of waves in a pool. One end has wave generators (the lasers) spaced appropriately such that resulting waves hitting the other end interfere just right and create a unified wavefront (same phase, amplitude, frequency).

NB: just my layman's understanding

Haha, this reminds me of all the stable diffusion "in the style of X artist" incantations.

Anthropic got rid of controlling the thinking budget by parsing your prompt - now it's a setting in /config.

They never parsed your prompt. The magic word reduces the probability that the token corresponding to the end of chain-of-thought will be emitted, which increases test-time compute.

Thanks for sharing! I've been gravitating towards this sort of workflow already - just seems like the right approach for these tools.

I've also never heard that use of "skill floor" before. The "floor/ceiling" descriptors imply min/max constraints.