ModelAufgelistetExtern

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,...

Quellecivitai.com/models/2837463

ArtLORABasismodellAnimaVersionBBewertung

Modellquelle

Art: LORA
Dateigröße: 33,3 MB
Basismodell: Anima
Version: v0.0.1
Aktualisiert: 27. Sept. 2026
Downloads: 261
Quelle: Civitai

Quellenbeschreibung

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.

Quellen

1 Quelle

CivitaiPrimärVersion 3238070

civitai.com/models/2837463

Verifiziert 17. Aug.

Modellartefakte

1 Artefakt

foreshortening_v0.0.1_0500_cosine_0200.safetensors

safetensors · BF16 · 33,3 MB · SHA-256 c9daae46fd4f…a40f · Civitai

Herunterladen

Quellenauszüge

1 Auszug

Note17. Aug.civitai.com/models/2837463

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