krea2 furry
The model was trained on approximately 1600 images of various types. To ensure versatility, it was trained on multiple styles, and secondary images were assigned lower probabilities.
Modellquelle
- Art
- LORA
- Dateigröße
- 327 MB
- Basismodell
- Krea 2
- Version
- vkrea2_furry_0716
- Aktualisiert
- 26. Okt. 2026
- Downloads
- 1776
- Quelle
- Civitai
Quellenbeschreibung
Perform longer training on a larger-scale dataset.
However, the different concepts are interwoven with each other and the learning difficulty varies. The model training might be overly intense and a lower intensity might be needed.
===
在更大规模的数据集上进行更久的训练
但是不同概念之间相互交错和学习难度不同,模型训练有些过度,可能需要低一点的强度.
Quellen
1 Quelle
Quellen
1 QuelleModellartefakte
1 Artefakt
Modellartefakte
1 Artefaktkrea2_furry_0716.safetensors
safetensors · BF16 (unverified) · 327 MB · SHA-256 adcd03cd80ee…de15 · Civitai
Download fileQuellenauszüge
2 Auszüge
Quellenauszüge
2 AuszügeSource context: 2485 downloads · Type LORA · Base model Krea 2
Source context: 1252 downloads · Type LORA · Base model Krea 2
