Trained for longer on the same dataset.
Tweaked training settings slightly.




SDXL VERSION: https://civitai.com/models/274070/facesitting-xl-girl-sitting-on-face
Trained for double the amount of epochs!
*All v1.1 example images can be imported into ComfyUI to see exactly how they were generated. Hopefully this helps with prompt engineering for the best scene.
**All v1.1 example images generated without extra embeddings, upscalers or detailers! I highly recommend adding embeddings, upscalers and detailers for the best composition.
***describing the girl sitting on the boy specifically and the boy lying on the object being sat on helps greatly with composition (i.e. 'sitting on a boy on a chair' paired with 'boy lying on a chair').
A LoRA trained on high quality images to produce satisfactory facesitting images in SD1.5. Multiple angles supported, but results may vary depending on the base model and strength.
A hi-res fix is highly recommended for the best results
Clip Skip: 2
Optimal Strength: 0.5-0.8
Trigger word: facesitting
Add other terms as well such as "sitting on chair" or "kneeling on a bed".
The LoRA attempts to take over any sitting, kneeling, or squatting actions. Adding the term "boy lying on floor" or "boy sitting on chair" may help if the male is not appearing. If the male is "sitting" against the object, the LoRA should re-arrange the scene to make his face the seat.
Trained for longer on the same dataset.
Tweaked training settings slightly.
1. 轉载模型僅供學習與交流分享,其版權及最終解释權归原作者。
2. 模型原作者如需認領模型,請通過官方渠道联系海藝AI工作人員進行認證。我們致力於保護每一位創作者的權益。 點擊去認領
