WAN 2.2
This one is pretty damn good if I do say so myself. Swapped out some of the other penis LoRAs for WAN 2.2 in my tests and this v2 blows them all away. Your results may vary, so look at the showcase prompts for help. This can create videos or images of male anatomy from a prompt, in realistic detail. It can also preserve the genitals if they are in your start frame for image to video workflows. Detailed anatomy prompting helps, see showcase for v1 and v2 for example prompts, or use local LLM Qwen VL or Grok for help with dick anatomy terms.
And it knows cum this time. No other LoRAs were used for showcase videos except for Lightx2v. For the cumshot, describe how much and exact details of where it goes. Beware saying 'massive cumshot' or you'll get a firehose like velocity and volume shooting out (see showcase).
You need both the high and low models in your workflows for video creation. The high noise model has its own version tab instead of the Required Components panel I orginally used. That would prohibit it from being used to generate videos with high+low loras on this site. The high noise part gets the motion, and low noise gets the details.
You can use the low noise with WAN 2.1 or its variants such as the SCAIL-2 or one of my favorites, Bindweave. You can create very high resolution images also the t2v model or with Magic WAN that are quite good (see showcase).
See showcase for prompts and workflows should be embedded in most mp4 files. I try to put the technique in them, t2v, or i2v. Some use RIFE or FILM interpolation for the frame rate and TensorRT or Nvidia RTX image scaling as well to get beyond 480p/720p. If there are some you like and the workflow is not available, let me know.
Check out https://coachbate.ai where you can see my latest work and follow me for free.
v2
Built on v1, adding 60 videos and the latest image dataset with the goal to fix the backwards or upside-down anatomy. It still can produce backwards glans, but before it would do it 90% of the time when viewing the underside of the penis, and now completely opposite, failing about 10% of my tests. Prompts can help if you get that. use 'detailed defined glans'. I guess it's hard to get rid of all the backwards dick heads in this world. Trained to a total of 15k steps, 20 hours of additional GPU time for version 2, stopping and adjusting along the way. Loads of work
v1
Trained on the same dataset as versions 1 of my Z-Image Turbo and LTX-2 LoRA, but for WAN 2.2 trained with the T2V model, which can be used to generate penises from your detailed prompt, or keep them in your scene if using i2v workflow.
Description
This is the high noise lora, trained with my latest dataset of ~60 videos and 200 images. Use this with the low noise lora in your workflows.
FAQ
Comments (4)
I have been unable to generate realistic looking penises using this. I thought that if I used a known good prompt, it might help me troubleshoot the issue. I decided to copy the exact prompt that was used to create the yellow speedos video in the showcase. I pasted it into WAN 2.2 T2V, added the LoRa, and tried generating videos. I tried using the prompt exactly as it appears in the showcase (i.e., without trigger words), I tried adding p3n15 to the beginning, I tried adding bwc to the beginning, and I tried adding both p3n15 and bwc. In all of the cases, the penis looked nothing like it did in the video you created, even though the prompt was identical to yours. I basically got mis-formed blobs or hotdog-shaped appendages without any definition. Do I need a secondary LoRa to go along with this? Do I need to adjust the strength of the LoRa? Are there required negative prompts I need to use? I am obviously doing something differently than what you did if the exact prompt gets you good results but doesn't get me good results.
that one is a FLF first frame last frame workflow. if you save the video mp4 to your desktop then file open in comfyui and select it, you should see the workflow. just pick any two images. you can use my krea 2 penis lora for example to generate them. I try to put the technique on each one - text to video or image to video. That one has the upscale workflow embedded so I just went and posted the source one for you that has the actual workflow used. It has some custom nodes that aren't published but all appear to be bypassed anyway. hopefully this helps, but key thing is you need start/end images to get amazing effects like this https://civitai.red/images/136050019
the latest generation of models don't seem to need or use the trigger words from my experience.
@coachbate I figured it might be a workflow issue. I will drag the image into Comfy later to see if I can figure it all out.