Description
High-quality character LoRA of Revy from Black Lagoon, trained for SDXL illustration models.
This LoRA focuses on maintaining clear facial identity, stable head structure, and consistent in-character expressions, aiming for reliable results across different prompts and compositions.
It is optimized for Illustrious-based SDXL models, I recommend Nova Anime XL for better results.
What this LoRA focuses on
Consistent and recognizable facial features.
Stable head proportions.
Natural, in-character expressions.
Reliable performance in SDXL illustration workflows.
General usage recommendations
Trigger word: revy_blacklagoonThe following values are general reference settings that work well with this LoRA.
Users are encouraged to adapt them to their own models, workflows, and project needs.
LoRA strength: 0.7 – 1.0
CFG: 6 – 8
Steps: 25 – 40
Sampler: DPM++ 2M or 2M SDE with Karras
This is my first LoRA of an anime character, if you notice any mistakes or things to improve you can tell me so I can improve it in future versions.
Description
This is an initial release focused on capturing Revy’s facial identity and overall character presence for SDXL illustration models.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.