Short description
A furry style LoRA inspired by Tianhua, favoring smooth contours, elegant character construction, and a polished digital finish. It is well suited to character-focused images that benefit from softer shaping and controlled detail.
Generation parameters
- Base model(s): Illustrious
- Trigger(s): Illustrious v1.0:
tianhua - LoRA weight:
1.0(recommended starting point; lower it mainly when stacking multiple LoRAs or when you want a softer style influence) - Sampler:
DPM++ 2M SDE Karras; tryEuler awhen you want a rougher or more graphic interpretation - Steps:
28–36 - CFG:
4.5–6 - Resolution:
1024×1024,832×1216, or1216×832 - If the style begins to overpower character identity or composition, reduce LoRA weight before changing CFG.
Prompt examples
TODO: Add 2–3 prompt examples validated against the current version.
Give me a hand
If Tianhua gives you good results with softer shaping, elegant character construction, or controlled rendering, post them so I can see what combinations are working. Difficult prompts are equally useful for spotting weaknesses; comments are welcome, and an upvote is appreciated if the LoRA earns it.
Suggestions
Recommended base from this profile: SweetIllustrious. For a controlled style blend, try Oposa style | [Illustrious] at a low secondary weight (0.2–0.45) and keep this LoRA as the dominant style.