This LoRA is designed to emphasize the buttocks and genitalia of female subjects (18+) in low sitting positions viewed from behind. It covers a specific range of seated poses where the buttocks rest on or near the ground.

This model is distinct from a standard "sitting from behind" pose (which typically implies sitting on a chair, bed edge, etc.). Here, the subject is low to the ground, with the rear prominently framed from behind.

Important:
Model is designed to assist in achieving the desired low sitting pose. You still need to write descriptive prompts that clearly describe the pose, angle, and subject. The LoRA will then reinforce and guide the generation toward the intended result.

Subject & Pose Description

The subject is depicted in a low seated posture, exposing her buttocks. Model emphasizes the glutes and genitalia from a rear viewpoint.

Variations include:

• Seiza (kneeling sit on heels)

• Wariza / petan zuwari (legs folded to the sides)

• Wide-spread legs with buttocks resting on the ground

Strength settings
0.2 - 0.5: Subtle, minimal pose change; gentle rear framing
0.6 – 1.0: Intense and reliable pose adherence; adds dynamism and stronger emphasis.
1.1 – 2.0: Aggressive posing with pronounced anatomical emphasis.
*At this level, it is essential to combine this LoRA with other LoRA models to recover fine details and maintain anatomical coherence. In many cases, this range results in full exposure of genitalia.

Image Format Recommendation

The vast majority of training images are in vertical orientation. Therefore, it is highly recommended to generate images in portrait mode (9:16 aspect ratio) for optimal composition and framing.

Trigger Words & Concepts

While the LoRA responds strongly to natural language prompts describing the pose and focus, it works best with concepts such as:

• low sitting from behind

• seiza

• wariza

• petan zuwari

• wide-spread legs

• buttocks on ground

• exposed anus / exposed vagina

• rear view

Best Practice

This model was trained exclusively on natural language captions generated by a vision model (Qwen, Ornith). No Danbooru-style tags were used in the training data.

For best results, use descriptive full sentences in your prompts rather than comma-separated tag lists.

Combining with Other LoRAs

To achieve a wider variety of poses and stylistic variations, it is strongly recommended to mix this LoRA with other LoRA models. This can introduce different body angles, clothing styles, environments, or artistic interpretations while retaining the core focus on the prone and recumbent rear‑glute emphasis.

License & Usage

• You are free to use this model in your projects, including merging or mixing it with other models.

• If you include this LoRA in any merge or mix, please give proper credit.

Support the Creator

If you enjoy my work and want to help cover the electricity costs required to train and refine these models, please consider supporting me:

Address: https://ko-fi.com/weirddreamer (Donations are always appreciated!)