note - if you were one of the first 20 people to download the workflow, try re-downloading the T2I workflow, I messed up by using a condition zero out node. Don't use those. - use a regular negative clip encode node.
note - the Loras attached to this checkpoint ONLY work with checkpoint v1.5 or higher. Note that the current Loras are just prototypes. My main focus is on the checkpoint and I will come back to the lora later. the retracted prototype is not very detailed at all, it is just an experiment
This model is best used with Turbo/Distilled Lora, otherwise you are unlikely to get good results https://civarchive.com/models/2324315/klein-4b9b-base-to-turbo-lora .
This creates realistic images in 4 to 8 steps!!
This can do text to image & image to image (up to 3 images) since it is just a finetune of Klein.
This model is trained slightly differently from my lora https://civarchive.com/models/2343427/klein-foreskin
It is slightly better at image to image outputs than the lora, though there are some things the lora does better such as taking a drawing and making it into a photo.
It retains more knowledge and is more realistic than just using the lora.
Version 1.9 is just trained longer than 1.5
Version 1.9 is just trained longer than 1.5. This makes it follow the prompt better with some things, but at the expense of realism. It started to overbake after 1.9 due to unbalanced dataset. Many things are still underbaked. I will now work on a version 2.0 with the goals of rebalancing and improving what is already here.
Version 1.5 is a remake of Version 1.0
During training of Version 1.0, I had some dataset errors such as missing control images, mismatched control sizes, missing captions and more. This resulted in several I2I issues where the model was not properly following directions.
I wrote a script to help validate my dataset images all had captions and no controls were missing. I trained from the ground up for Version 1.5. I have tweaked a couple of things which result in following prompts more closely, however Version 1.0 may have slightly different outputs which makes it worth downloading too.
I have paused training to work on a circumcised/retracted foreskin penis lora (that pairs with this checkpoint),
I will also test the capabilities of 1.5 to determine areas of weakness and then continue training from here to push it further.
What can this model do?
This is designed to give easy to use control with natural language. It is trained on the following conceps. I am going to see how much ability I have to continue finetuning to improve the results:
works very well
1. nude male, pantless male, shirtless male, penis exposed through fly, pants pulled down,
2. penis, erect penis (needs some more training on erect)
3. foreskin, (i2i) add foreskin
4. masturbating (borderline needs more to training to finetune this more).
5. grabbing foreskin
6. inserting things in foreskin like fingers, objects
7. pubic hair (i2i) add/remove pubic hair/body hair
8. Cock rings
9. Cum/ Cumming/ Ejaculating Cum, Cum is on face
Version 1.5 is better at:
1. converting images to styles
Most of the way there and will often work
1. masturbating
2. erect penis, though I want to work on this more
partial training/ needs more work
1. (i2i) male penis erect/ make penis flaccid
2. fellatio, tongue in foreskin, sucking foreskin
3. (i2i) remove foreskin
4. long foreskin
5. glans
6. fleshlight
7. Camera views like point of view
training didn't stick
1. short_foreskin
2. make penis smaller
3. increase foreskin length
Items that were forgotten from base model
1. (i2i) make into a photo/ make into anime
2. text is sometimes messed up
no training yet
9. autofellatio
10. anal sex
11. circumcised
12. retracted
Plan
I will plan to make a lora for circumcised penises.
I will plan to expand my dataset and continue training 1.5 into 2.0 to fin
Description
workflows
FAQ
Comments (17)
Is Checkpoint now specialized in penises, so to speak? Or can I use it as a substitute for Base?
You would use it as a substitute for base. It still retains all of the base knowledge of Klein but is finetuned to add knowledge of penises.
There are some tasks the base can do better.
Make sure to use it with the turbo lora and see my workflows
@Epispasm Great, thank you. I'll give the checkpoint a try. It would be nice to have different sizes (unless the sizes are more authentic than with SDXL). Let's see if I can get some nice TGirls with Inpaint. 😍
Thank you for your work!
as it should be. All base models should specialize in penises; the rest of the world comes secondary.
@Epispasm "There are some tasks the base can do better." Like?
@ss9999 I retrained the model, but the original had some dataset errors with missing control images, so the image to image edit of v1.0 is not as strong as the base. I remade the model after correcting the errors and it is nearly as strong as the base.
That said, my anime style tends towards semi-realistic proportion and the base model has the more stylized traditional anime. The longer I train, the worse things like changing styles to things like simpsons style or other cartoon style gets weaker because my dataset does not represent those styles well.
@Epispasm Thank you for the explanation. Losing anime wouldn't bother me at all but I understand that it's popular.
Thanks for your work. I'm convinced Klein 9b is going to do a better job than Zit. So I'm really looking forward to future updates of your model. Currently testing this one. It's great that you can start from a checkpoint that already knows male stuff. Thanks!
Let me know if you need any help!
I love this but my download manager won't work with a civitai link, and my internet can't handle that large file as a direct download. Maybe this is on hugging face? Or maybe you could extract a lora?
I've tried extracting it as a lora and didn't work, but will continue to look for a way to do so.
I have a trained lora which is almost as good. Link is in the description of this model.
@Epispasm could you upload it somewhere, maybe like GitHub? CivitAI blocks my download manager (nevermind, I got it)
this looks so flexible, which is what I've always wanted; a flexible penis lora that can do different shapes sizes and positions.
Nice, this checkpoint is better and flexible than most other loras on the site, including Zimage Loras. I think we need circumcised penis LoRA/checkpoint and I belive you are the one of the members that can properly do it considering the quality of this.
I'm working on a circumcised/retracted penis lora that would go on top of this checkpoint, but probably wouldn't work with other checkpoints/base model. If it works, I'll upload it when its done
@Epispasm glad to hear. Thanks.
@Epispasm Good idea. That would make it perfect. Retracted foreskin would be awesome.