Daniel Solisさんのイラストまとめ

LookingGlassAI outputs/inputs in square format. I think it crops inputs to the center before training. Thus, I have a lot of birds that don't quite fit their frame.

The Giant Barker
The Goliath Flounder
The Flecked Behemoth
The Beetle Burglar

The Belter
Cloud Strangler
Sailor's Moon
The Flightless Biff

The Freelance Bartender
The Whole Wheat Breadbox
The Burrowing Evildoer
The Flammable Finch

Common Benchpress
Flagrant Scofflaw
Rusted Rooter
Wooden Spoon and False Wooden Spoon

The Flying Nudibranch (shown with chick)
Jerry's Neighbor
Lovely Lady
The Hostile Witness

Humpbacked Quail
Captain Falcon
The Interrupter
Warped Dangler

Turner's Hooch
Red-Breasted Eye-Poker
Giant-Headed Bug-Stabber
The False Moffat

See, birders, you could call these "Crested Tweed-Foot" or "Pale-Thighed Webhead" or "Open-Mouth Manwich" and I'd believe you.

Given the widely varying morphology, I feel ill-equipped for judging the success of the AI's training. I just have a gut sense of what's "plausibly bird." The best I can do is like "Uh... Beak? Yeah, somewhere. Wings? At least 2. Funky plumage? Yep. Plausibly bird. Next!"

Since birds often appear in the context of flowers, leave, and branches, there were often some odd blends of all three. I'm surprised it didn't occur more often, to be honest. It's pretty good at knowing leaves and wings go together. The beaks and heads give it trouble though.