V4.2 uses the same dataset as V4.1 and V4.0, but I removed all hardcore images from the dataset, so this is a softcore only LoRA now. It seems the genital quality is even better. Pubic hair is the default in this LoRA. I will train a hairless version later. I reduced the rank from 64 to 32 to reduce overfitting of the face.

重新train了一版V4.2，使用的是V4.1，V4.0 相同的数据集，但是去除了hardcore图片，所以变成没有性交场景的lora。 逼都是同一个人的，所以只能看作逼的character lora? 变化的是：同一个逼阴唇闭合掰开的不同形态，不同视角下的形态。。。
感觉这一版逼的渲染质量要好一些。🤣

I continued training V4.0 to 10,000 steps and released it as V4.1. It seems more robust now at controlling whether pubic hair is present using the hairless_pussy or pubic_hair tags. The detail inside the labia has also improved. V4.0 (trained for 5,500 steps) seemed a bit underfit. Sorry for updating this LoRA so frequently. I’m still finding the right parameters to train the Krea2 LoRA. Hope you like this lora.

Lora strength: 1.0 - 1.5
If the sex scene is not triggered, increase the lora strength.

In V4.0, I added more images of hairless pussies to the dataset, making it easier to generate no-pubic-hair pussies with the tag hairless_pussy

I also added many front-view innie pussy images to the dataset, so this LoRA can generate innie pussies now with the tag innie_pussy

中文用户请查看例图prompt

One issue I observed in V1.0 and V2.0 was that the labia appeared excessively dark in generated images, unlike their appearance in the training dataset. This likely resulted from overfitting due to my original training approach: I masked out the genital region in full-body images, assigning a loss weight of 1.0 only to the masked area and 0.0 elsewhere.

In V3.0, I removed this masking strategy and added additional sexual pose variations to the dataset. Hope you enjoy the improvements!

V1.0 dataset contained only solo female images, causing conflicts with other hardcore LoRAs and checkpoints.

V2.0 includes 200 images of sex scenes to the dataset to improve compatibility.

lora strength: 1.0 - 1.5

If mosaics appear, increase the LoRA strength.

Sex positions included:

• Reverse Cowgirl

• Missionary

• Doggy Style

Krea2 Pussy LoRA. Trained on the same dataset as: Z-Image - Better Pussy & Poses
Workflow (krea2_simple_worflow.json) attached to the optional files.

No need to use conditioning node or safety filter bypass lora！

I feel like Krea2 LoRA training is much easier than Z-Image. I got good pussy quality with just 2,000 steps.

• Base model (Krea2 Turbo): https://huggingface.co/Comfy-Org/Krea-2/blob/main/diffusion_models/krea2_turbo_fp8_scaled.safetensors

• Text encoder: https://huggingface.co/Comfy-Org/Krea-2/blob/main/text_encoders/qwen3vl_4b_fp8_scaled.safetensors

• Vae: https://huggingface.co/Comfy-Org/Krea-2/blob/main/vae/qwen_image_vae.safetensors
  

Dataset: 311 unique pussy images (163 close-up; 20 median close-up; 127 full-body)

Steps: 2000

Pussy lora strength: 1.0 - 1.5
CFG: 1.0
Steps: 8
Sampler: euler
Scheduler: simple
Resolutions: 1024/1536/2048

⚠️ This LoRA was trained on Chinese captions. English might work since Qwen3VL is bilingual

Required trigger word: anatomy_detail

Subject: 东亚年轻女性 (young East Asian woman)

Control Tags:

• Framing: close-up / medium / full body

• Labia: 阴唇闭合 / 阴唇被掰开内部可见 (labia closed / labia spread open, inside visible)

• Pubic hair: 阴毛可见 / 没有阴毛 (pubic hair visible / hairless_pussy)

• Legs & pose: 双腿打开 / M字腿膝盖弯曲 / V字腿膝盖伸直 / 站立一字马 / 横向一字马 (legs spread / M-legs knees bent / V-legs knees straight / standing split / horizontal split )

• Hands: 双手绕过屁股外侧掰开阴部 / 双手放置于下腹部掰开阴部 (hands around butt spreading genitals / hands on lower abdomen spreading genitals)

• Views: front / side / back view

prompt = “anatomy_detail” + framing + subject + labia state + pubic hair state + legs + hands + view + other details

Sample prompt：

anatomy detail, full body, East Asian young woman, closed labia, visible pubic hair,  legs spread apart, M-legs knees straight, hands around butt spreading genitals, front view, lying on a red plastic track, eyes gazing directly at the camera, sneakers, sportswear, short sports skirt, ponytail