I can guide you with the best practices, tips, and tricks to achieve your goal in your Stable Diffusion training. Take a look at my Patreon, subscriptions for just $5. Exclusive content. Patreon. :)
About:
Hello!
Have you ever been embarrassed or insecure about taking a picture of your š„ and sending it to someone?
Your problems are over!
Now you can just generate as many super realistic dongs as you want with this LoRA and spread them around. š
It was trained in 768x768, using captions and 166 (for now) images.
As usual, I make a test version without enhancing the photos, to assess viability. This one seems promising, so I'm going to upscale the dataset and add more content (God only knows when, because I have ADHD).
DO NOT FORGET THE DASHES IN PROMPT if you want to replicate the images I did.
The demo images aren't edited, but they are cherry-picked and generated in A1111 WebUI (v1.8 RC), using hires-fix (0.25 ~ 0.50 denoising), 4x_NMKD-Siax_200k (or 4x-UltraSharp) upscaler.
Suggested Settings for Inference:
Model: PicX_real
Positive: dick-pic, large penis, holding-a-thick-staff, first-person-pov, every-day, (((Ultra-HD-quality-details))) <lora:Dick_Pic_by_IsnAI:1:0.7)
Negative: morbide-body-parts, snap-fingers:2, apoplexy, wrong-placed-limbs
Sampler: DPM++ 2M Karras
Steps: 28
CFG: 6~7 got best results, but also works with 5~6
Resolution: 512x768
LoRA Weights: 1:0.7
NoteĀ¹: As you can see, the LoRA tag has two weights: <lora:Dick_Pic_by_IsnAI:1:0.7)
This is a feature of the A1111 (which many people aren't aware of), but you can set separate weights for the UNet and the Text Encoder. The TE is always a pain in the ass to get the training right, so it's usually better to reduce its weight in the inferences rather than having it undertrained.
NoteĀ²: You will see big variations in style and images depending on the base model used and minor adjustments in resolution.
NoteĀ³: If your images are getting weird and bizarre, you probably didn't reduce the TE weight. If you aren't using A1111 WebUI, you can do the common weight reduction: <lora:Dick_Pic_by_IsnAI:0.7), but you will need to test which weight will suit better.
Triggers:
Main Tags Used on Training: dick-pic, penis, first-person-pov, holding-a-thick-staff
Secondary Tags Used on Training: hairy, shaved, uncut, view-from-the-side, legs, hand, fingers, feet, toes