For the next few months (or until I get bored), any experimental film festival accepting submissions is getting an exclusive Stop Making Sense made just for their festival. If you curate a festival and are interested please get in touch.
A little more fun. Some Bill Brand vibes.
While LLM tokens feel much less expensive now I'm still very aware of my image gen spend. Trying to find unique ways to extend a few dollars of image gens.
once again everyone is going crazy for opus 5.5 like it fundamentally changes everything. After a few days its a good stepwise improvement for me (like always). still has some claudeslop, still stops too soon, etc.
Agents are already so much smarter than me.
To determine whether it was accurately generating images of people in motion it decided to use SAM2 to detect people and once it could no longer detect them it was blurred enough.
Training image models? I am releasing my digital asset manager for image model training free/open source. github.com/latentwill/modelf…
It's designed to be agent first, with a CLI, letting you easily tag, sort, make grids, connect to services etc.