Willhem-V1.1 es un modelo LoRA para Stable Diffusion 1.5, diseñado para generar retratos realistas de un personaje masculino. La V1 tenía unos fallos que persistían y arreglé. ES la V1.1 ya que use el mismo dataset.
Recomendaciones:
Fuerza del LoRA: 0.7~0.8
Pasos: 30
CFG Scale: 7
Sampler: DPM++ 2M Karras
Modelo: Realistic Vision V6.0 B1
En el inicio del prompt: Willhem (Willhem-V1.1:0.7) o Willhem (Willhem-V1.1:0.8)
////////////////////////////////////////////////////////////
Willhem-V1.1 is a LoRA model for Stable Diffusion 1.5, designed to generate realistic portraits of a male character. The V1 had some persistent issues that I fixed in V1.1, since I used the same dataset.
Recommendations
LoRA strength: 0.7~0.8
Steps: 30
CFG Scale: 7
Sampler: DPM++ 2M Karras
Model: Realistic Vision V6.0 B1
At the beginning of the prompt: Willhem (Willhem-V1.1:0.7) o Willhem (Willhem-V1.1:0.8)
Description
Use el mismo dataset e hice nuevos ajustes en el entrenamiento, ya que en mis pruebas el modelo V1 tenía unos fallos, los cuales persistían.
FAQ
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.