Generative Models Explored for Gabor Wavelet Image Representation
pixlpa · x · 2026-08-24
A research project gabormodels has been released, exploring generative models over Gabor-atom image representations. Instead of per-image fitting, the repo documents twelve attempts to learn and generate these atom sets using machine learning. The goal is to build creative tools that leverage this representation, offering unique creative possibilities through parameter manipulation, similar to working with audio synthesis.
More from Multimodal
- 56s Suspense Video Generated by Minimax H3 Model — rileygstaliger · 2026-08-24
- Generating 'talking' ASCII landscapes with Opus: the Word Layer technique explained — repligate · 2026-08-24
- Creating an Alien Short Film and Music Video with Local MiniMax H3 — No_Taste_4102 · 2026-08-24
- Refining Minimax Video with Wan 2.2: Removes Smudges and Adds Custom LoRA Support — GrungeWerX · 2026-08-24
- Why Music Hackers Value Open Weights in Stable Audio 3.0 — jordiponsdotme · 2026-08-24
- Fable Shows Prodigy Sculpting Skills, Outperforming Opus 5 in Face Generation — repligate · 2026-08-24