v2
Add a couple images to the dataset and modified a few captions then fine-tuned LoRA by training for 10k steps total. Try training with this base model - it's fast and does a great job. You can also give the image a pass through Z Image Turbo if you prefer its looks better given the difficulty many have reported creating Z Image Base loras. (btw I think my Z Image base LoRAs are just as good as my Qwen ones, sometimes come out better even)
v1
I'm surprised at how well this model did. Without any LoRA it generates the least monsterous dick I've seen, and with training and the right sampler/scheduler you can get some good D out of this. And it doesn't put the head on backwards nearly as often as some of the other models, but I am always tweaking my dataset + captions, so maybe that helps as well.
Not sure if trigger word is always needed, but I changed from using bwc to p3n15 for this one since Klein 9B often thought I wanted a black and white image not a big white cock image.
Description
Initial release
FAQ
Comments (5)
It needs some more work, but it does work for now.
please post your outputs below (add post to gallery)
I hope it helps.
https://civitai.red/posts/28076775
Thanks a lot for sharing this — male anatomy LoRAs are rare precisely because most creators don't publish this kind of thing (probably 90% of what's out there is female anatomy), so the effort is really appreciated.
Honest feedback: the penis itself looks great, but the testicles/scrotum still come out pretty artificial. It's something I've noticed across pretty much every male anatomy LoRA I've tried, not specific to yours — but it's the detail that still breaks the realism. Would love to see it addressed in a future version.
i agree. I did add a few images for better balls but looks like i need more. maybe more detail in the prompt too would help