KinkAI
patreon
New LoRA: Futa TakerPOV Blowjob
🕑 Added 2023-04-06 00:07:27 +0000 UTCNew LoRA is up on CivitAI: Futa TakerPOV Blowjob.
As I mention on the model page, this one is pretty straight forward to use.
Use 'takerpovbj' as the general trigger.
'Close up', 'extreme close up', 'looking up' and 'looking ahead' are used to control the perspective, but you don't need to use any of them.
Use 'looking ahead' and 'extreme close up' together, to get the real close up shots. Avoid describing any facial features/hair etc. in this case, or it won't work properly.
If you're getting too many images where her head is out of frame, use a taller aspect ratio, 640x768 for example.
Also reacts well to 'small/medium/big/huge breasts'.
It was also trained to react to 'grabbing you', but I didn't have much luck prompting for it.
Something to work out with the next version.
That's about it. Looking forward to seeing what you can make with it!
Settings I used for the previews:
Model: UberRealisticPornMerge
Sampler: DPM++ SDE Karras
CFG scale: 5
Steps: 30
Comments
Weird, it keeps deleting the code I'm pasting in. I'll try sending it in a PM
Adam Glenn
I don't think I've ever gotten any Lora working 100% but it could be the problem is Easy Diffusion. I'll give Automatic1111 WebUI a try and see if I can get better results from that.
Hey Adam, I haven't used Easy Diffusion, so I can't know for sure what's going wrong there. But I have a few things you can try. The LoRA should work with most models, but to rule it out you should use UberRealisticPornMerge. Then, and I'm not sure if this applies to Easy Diffusion, but in Automactic1111 WebUI the LoRa needs to be activated in the prompt. That should look like this: One thing to note here is that CivitAI changes the filenames when I upload a model, so this activation prompt is different from what's shown in the metadata on my example images. The one I'm mentioning here should work though. Are you having trouble using any other LoRAs? I also saw that there's a NSFW filter option in Easy Diffusion... maybe that's the issue?
Adam Glenn
I'm pretty new to creating images with stable diffusion. I've downloaded the lora and I've tried using positive/negative prompts from one of the pictures you posted on Civitai. I'm not using your seed so I don't expect to recreate the image exactly but I don't get anything like the results you've posted here or on Civitai. Am I using the wrong Model or something? I have the Lora selected in Easy Diffusion and I've set the LoRA Strength to 1 or as low as 0.05 but it doesn't seem to change the outcome.
