This LoRA was trained using 112 reference images featuring extreme foreshortening in order to amplify the effect as much as possible. As a result, v0.0.0 produces strong perspective distortion on nearby objects, similar to the appearance of a fisheye lens.

Concept > Foreshortening

Tweaks.Changes from v0.0.0:<ul><li>Added 58 images to the dataset (112 → 170 images), featuring highly dynamic action scenes, including motion blur.</li><li>Training settings<ul><li>Increased dim from 4 to 8.</li><li>Changed the training schedule from cosine 1000 to constant 500 + cosine 200.</li></ul></li></ul>dim8/alpha8, UNet LR 1e-04, AdamW8bit, warmup 0, constant 500 + cosine 200, 512² resolution, 170 images.

Files with SHA256: c9daae46fd4f97210e04f8ccafb2cd8ce404c47349978319698495e73d3ea40f