This LoRA is designed to emphasize the buttocks and exposed genitals (anus or vagina) of female subjects (18+) from a rear viewpoint.
The model specifically focuses on poses where the subject actively spreads her buttocks, thereby revealing the intimate areas. The aesthetic is highly erotic and explicit, maintaining clear emphasis on both the glutes and the exposed genitalia from a dorsal (behind) perspective.
Subject & Pose Description
The subject is depicted from behind, actively spreading her buttocks to expose the anus or vaginal area. The composition consistently frames the glutes and genitalia as the primary focal points. Variations may include slight spreads, full exposure, or dynamic stretching poses, all captured from a rear angle.
For greater variety in poses, it is recommended to combine this LoRA with other LoRA models that introduce different body angles, environments, or stylistic elements.
Strength
0.2 - 0.5: Subtle and minimal pose modification; a gentle hint of the spread and exposure, with the primary pose remaining relatively modest.
0.6 - 1.0: Intense effect; guarantees the spreading pose with dynamic framing, clear exposure, and confident anatomical presentation.
1.1 - 2.0: Aggressive and highly pronounced posing with full, explicit exposure.
*At this level, it is strongly recommended to use other LoRA models (bypass) to recover fine anatomical details, textures, and overall composition coherence.
Image Format Recommendation
Most images in the training dataset were processed in vertical orientation.
Therefore, it is highly recommended to generate images in portrait mode (9:16 aspect ratio) for optimal results.
Training & Captioning Methodology
Each training image underwent detailed analysis and captioning, taking approximately 4 minutes per image across 8 distinct sections.
Captions frequently exceed 300 words to capture every nuance of the composition, including object and body descriptions, environment, and camera 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:
spreading buttocksexposed anusfrom behindrear viewspread cheekshands spreadingass squeezed
Best Practice
This model was trained exclusively on natural language captions generated by a vision model (Qwen). 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 seated‑rear focus.
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!)
Description
Dataset Size:
120 high-quality, manually curated images
Data Processing:
Images were meticulously filtered using advanced duplicate removal tools to ensure maximum variety and uniqueness.
The model was intentionally overtrained to gain more detail. If the results are unsatisfactory, then reduce the model strength or use the LoRA bypass.
Captions:
Tagging was performed using Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_M


