Skip to content
ModelListedExternal
Download

Concept > Foreshortening

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,...

KindLORABase modelAnimaVersionBgrade

Model source

Kind
LORA
File size
33.3 MB
Base model
Anima
Version
v0.0.1
Updated
Oct 20, 2026
Downloads
261
Source
Civitai

Source description

Tweaks.

Changes from v0.0.0:

Added 58 images to the dataset (112 → 170 images), featuring highly dynamic action scenes, including motion blur .

Training settings

Increased dim from 4 to 8 .

Changed the training schedule from cosine 1000 to constant 500 + cosine 200 .

dim8/alpha8, UNet LR 1e-04, AdamW8bit, warmup 0, constant 500 + cosine 200, 5122 resolution, 170 images.

Sources

1 source
CivitaiPrimaryVersion 3238070
civitai.com/models/2837463

Verified Aug 17

Model artifacts

1 artifact

foreshortening_v0.0.1_0500_cosine_0200.safetensors

safetensors · BF16 · 33.3 MB · SHA-256 c9daae46fd4f…a40f · Civitai

Download

Source excerpts

1 excerpt

Source context: 518 downloads · Type LORA · Base model Anima