Recommend:
Sampler: ddim
Scheduler: beta/beta57(for more realistic)
Steps: 8 - 12
HerRAW 是一个面向 Krea 2 的通用女性真实摄影 LoRA，目标是在尽量保持原始 Prompt、人物特征、构图和场景控制能力的前提下，提升女性人像的自然摄影质感。
本模型无需触发词。加载 LoRA 后，可以直接使用正常的自然语言 Prompt 进行生成。
v0.1 是 HerRAW 的第一版实验性基线模型，主要用于验证数据训练通用女性摄影 LoRA 的可行性。
HerRAW is a general-purpose female photography LoRA for Krea 2, designed to improve natural photographic realism while preserving as much of the original prompt, subject characteristics, composition, and scene control as possible.
The model requires no trigger word. Simply load the LoRA and use normal natural-language prompts.
v0.1 is the first experimental baseline of HerRAW and is primarily intended to evaluate the feasibility of building a general female photography LoRA from training data.
Description
What’s improved
Better face diversity — less tendency for different characters to converge toward the same face.
More natural skin — reduced overly smooth / plastic-looking skin, with more believable texture, tonal variation, and highlights.
Improved East Asian facial aesthetics — more balanced and natural-looking features without forcing a fixed AI beauty template.
Stronger photographic realism — improved hair, clothing materials, lighting, and overall realism in close-ups, half-body, full-body, and environmental portraits.
相比 0.1：
人脸多样性更好：减少不同人物逐渐长得相似的问题，更好地保留原本的脸型和气质。
肤质更加自然：降低磨皮感和塑料感，增加更真实的肤色变化、皮肤纹理和高光表现。
东亚女性面部更协调：提升整体审美，同时尽量避免固定的“AI 美女脸”。
整体摄影感更完整：发丝、衣料、光线以及半身、全身、环境人像都有进一步改善。