Asked two AIs about solving a least square problem. one suggested Gauss-Seidel to solve the linear system, while the other suggested QR decomposition. And the former one failed.
ai corps disvalue and discredit others’ works used for training and plagiarism without consent, to gather all values and credits to their own system, while don’t allow their models to be distilled.
maybe the post referred to sdf modeling directly by codes like what iq did. For general sdf modeling, artists can make brilliant models with intuitive sdf toolset as well.
In fact, I'm pretty sure the only person in the world who can build models like this by hand is @iquilezles. My AI-assisted process borrows (and outright steals) from his work.
In that spirit, I dub the model “Inigo the Dragon”: https://t.co/H8G3FVBEQv
Sorry @iquilezles! [3/n]
The sight of this divine carving has lived with me since I was very young, and only now have I had the courage and tools to make it myself. This Chozo is a combination of how I remember him, and a few other designs.
#Metroid#MetroidDread#MagicaCSG#artㅤㅤㅤㅤ
-“you don’t have to develop your own brain any more because our model is superior”
-“but we may ban your access to our model in some scenario and you will become useless”
for curiosity, I throw some of my novice sketches into some dated(?) oss image generators, the results are kind of interesting...there are some thoughts and options about the process which require a thread of posts, so for now just leave some comparison here...(1/3)
@IY0YI exactly:) artwork is a medium for the communication between artists and audiences. we want to read the biography of the artist, understand the backstory of the work, appreciate the painting/sculpting skills, share the same emotions, which are lacking in generated contents.
@Flipframe@MamaMajikina because we have to try the new stuffs by ourselves to understand the pros and cons objectively:) on the tech side, it's still amazing that the engine can "recognize" and modify contents of images by imprecise natural language.
@KamiSawZe it can be modified to some degree by text prompt, but the feeling is hard to be described precisely in languages. the only thing you can do is praying that the engine randomly generates what you expect.
@Flipframe@MamaMajikina thanks and not intend to do so. it’s more like sending your sketches to other artists (whose artworks are unfortunately trained by ai) and let them to redraw it and decide shading/contents base on their own style and taste, which ruins the fun and meaningful part