### Lulu01 - SDXL Character LoRA
A realistic LoRA model of [Meno tvojej postavy] trained on SDXL Base 1.0.
Dataset consists of 35 high-quality, curated images.
Trigger Word: lulu
Base Model: SDXL Base 1.0
### Recommended Generation Settings:
* LoRA Weight: 0.75 - 0.9 (0.8 is the sweet spot)
* CFG Scale: 5.5 - 7.0
* Sampling Steps: 25 - 30
* Sampler: DPM++ 2M Karras or Euler a
* Resolution: 1024x1024 (or native SDXL aspect ratios)
### Prompting Tips:
* Clothing Flexibility: To change outfits, simply specify them in the prompt (e.g., lulu, wearing a red hoodie, jeans).
* Styling: Works best with realistic and cinematic checkpoints (Juggernaut XL, RealVisXL).
Description
Initial release of the character LoRA.
Trained on 35 high-quality curated images using SDXL Base 1.0 for best compatibility across different realistic checkpoints.
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.