First entry in my BDSM related series of LoRAsWorks well in conjunction with my <a target="_blank" rel="ugc" href="https://civarchive.com/models/20120/pov-missionary-vaginal-creampie-lora">POV Missionary Vaginal + Creampie LoRA</a>If you feel like supporting my work, please consider visiting my Patreon to get access to more detailed instructions on how to get the most out of my models and have a say in what's up next: <a target="_blank" rel="ugc" href="https://www.patreon.com/KinkAI/about">Link</a>.It can do both 'face up' and 'face down', if you prompt it for that.Update:I worked on improving the dataset to have more high res images for solving the issue with the bad faces. It has helped, but I found that it mostly comes down to the resolution you render at, so I recommend 640x640 minimum for frontal shots.The faces are quite far back in the scene making them very small, too small for the AI to handle on smaller resolutions it seems. If you have any hints on how to fix that, please let me know.I also went through the training images and increased the contrast of the rope against the bed (making it black when it was white on white), and added the rope color to the tags. It is a lot more reliable with drawing the ropes to the edge of the bed.Especially when you prompt it with 'rope' or 'black rope' etc.Recommended LoRA Strength: 0.6-0.8Based on UberRealisticPornMergeIf you like this, you may also like<a target="_blank" rel="ugc" href="https://civarchive.com/user/KinkAI"> my other LoRAs</a>.

BDSM - Tied to bed LoRA

<ul><li>Improved dataset</li><li>Improved tags</li></ul>

TiedToBed-v2.safetensors

 - Tied to bed LoRA

Bedrope

TIEDTOBED
FACE UP
FACE DOWN
FRONTAL
AT ANGLE
CLOSE UP
ROPE
BLACK ROPE
WHITE ROPE

Sleeptyed

First entry in my BDSM related series of LoRAsWorks well in conjunction with my <a target="_blank" rel="ugc" href="https://civitai.com/models/20120/pov-missionary-vaginal-creampie-lora">POV Missionary Vaginal + Creampie LoRA</a>If you feel like supporting my work, please consider visiting my Patreon to get access to more detailed instructions on how to get the most out of my models and have a say in what's up next: <a target="_blank" rel="ugc" href="https://www.patreon.com/KinkAI/about">Link</a>.It can do both 'face up' and 'face down', if you prompt it for that.Update:I worked on improving the dataset to have more high res images for solving the issue with the bad faces. It has helped, but I found that it mostly comes down to the resolution you render at, so I recommend 640x640 minimum for frontal shots.The faces are quite far back in the scene making them very small, too small for the AI to handle on smaller resolutions it seems. If you have any hints on how to fix that, please let me know.I also went through the training images and increased the contrast of the rope against the bed (making it black when it was white on white), and added the rope color to the tags. It is a lot more reliable with drawing the ropes to the edge of the bed.Especially when you prompt it with 'rope' or 'black rope' etc.Recommended LoRA Strength: 0.6-0.8Based on UberRealisticPornMergeIf you like this, you may also like<a target="_blank" rel="ugc" href="https://civitai.com/user/KinkAI"> my other LoRAs</a>.

Files with SHA256: 7ef10731a5a95999c247c880df2b26fa8d15b4dc46e2b8064065a3f8839160d0