Create penises with text to image workflows using the Moss-Image Base or SFT models. I trained this on the base model and it can be used both models.
The model itself can generate decent penises without my LoRA, but mine trains it to look even better with my custom dataset of good D.
TIPS for Prompting Moss-Image
Avoid using colors that otherwise work fine for other penis LoRAs such as saying it casts " deep reddish-purple tones" - it will look like blood or scabs. Took me a second to find what was wrong with some of my outputs that worked great for other models.
Some models over vein it up if you mention veins, like Krea2, but if you use 'prominent vein(s)' it will be bluish purple and nothing I've seen on a dick before. You can say minimal veins and it comes out fine.
Quality Tips
I'm getting amazing quality using the SFT model with the default ComfyUI template, but changing a few settings:
sampler: res_multistep
scheduler: simple
30 steps
cfg 4
dimensions: 4 megapixels, 8 seems to work also
All my models have at least one free preview generation available on them for you to try out. I recommend you remix one from my showcase following that general prompt.
Troubleshooting and Feedback
If you encounter problems, please begin by trying to recreate one of my showcase examples using its embedded workflow. Whether that workflow works on your system will tell us a lot and make troubleshooting easier. If you can reproduce the showcase but have trouble with your own images or prompts, let me know what happened and include your settings if possible.
I’m always open to suggestions for improving my models. If you own suitable sample material that you would like me to consider adding to the training dataset, please reach out. Concrete examples are much more helpful than general suggestions.
Description
v1 trained against MOSS-Image Base model and works best on STF model