For the best experience, use it together with a futanari friendly checkpoint like Futanari Factor
This is an "improved" version of the FutaVeinyV6 that has more penis and testicles sizes. The adapter was trained using LoKr and was tested together with models that are already able to draw futanaris without much effort like abyssFuta, bb95-furry-mix, fluffyrock and their merges.
How to use
Edit the "SIZE" to the size you want to use.
Penis sizes:
small penis (WIP)
penis
large penis
huge penis
gigantic penis
Testicles sizes:
testicles
large testicles
huge testicles
gigantic testicles (WIP)
If the size slider doesn't seem to be working well with your prompt, try adding some weight to the token:
futanari, veiny penis, (gigantic penis:1.4), (huge testicles:1.2)Optional:
You can add "erection" or "flaccid" to your positive or negative prompts to control the dong status.
(WIP) If you like some saggers, add "sagging testicles" to your positive prompt.
(WIP) Add "foreskin, phimosis" to your positive or negative prompts to change the dong sheath.
Your feedback is appreciated! Its going to help a lot with tracking what checkpoints are working the best to produce the best dongs and what I need to change in the next iterations of this lora.
Development notes:
The training images were tagged using conv2 and swinv2 at the same time and then merged together and the duplicate tags removed.
Every caption was revised by me and the concept tokens were reordered to be used with keep_n_tokens.
Every image was cleaned of signatures and watermarks using lama cleaner and photoshop.
Censored images were redraw using deepcreampy and then manually retouched using manga studio.
5%~10% of the dataset is reserved for AI generated images made by me that were upscaled and manually retouched using manga studio and a drawing tablet. It helps to augment some concepts that don't have enough good pictures and achieve that specific futanari aesthetic I'm looking for.
I took 1 month to assemble, clean, redraw and tag the dataset, but the training and testing process is even more time consuming. To help with that, I'm also trying to code a tool to help me evaluate the testing grids, find the best epochs and track what worked or not between batches.
Description
700mb worth of quality meat!
This one is still not compatible with comfyUI. Use it in auto1111 for now.
Not much changed besides switching algo to full module. You can try this version out if you think your dongs aren't good yet
FAQ
Comments (14)
I got this error message. what can i do?
activating extra network lyco with arguments [<modules.extra_networks.ExtraNetworkParams object at 0x7f1f6eeac3a0>]: AssertionError Traceback (most recent call last): File "/home/studio-lab-user/sagemaker-studiolab-notebooks/stable-diffusion-webui/modules/extra_networks.py", line 75, in activate extra_network.activate(p, extra_network_args) File "/home/studio-lab-user/sagemaker-studiolab-notebooks/stable-diffusion-webui/extensions/a1111-sd-webui-lycoris/extra_networks_lyco.py", line 90, in activate lycoris.load_lycos(names, te_multipliers, unet_multipliers, dyn_dims) File "/home/studio-lab-user/sagemaker-studiolab-notebooks/stable-diffusion-webui/extensions/a1111-sd-webui-lycoris/lycoris.py", line 488, in load_lycos lyco = load_lyco(name, lyco_on_disk.filename) File "/home/studio-lab-user/sagemaker-studiolab-notebooks/stable-diffusion-webui/extensions/a1111-sd-webui-lycoris/lycoris.py", line 458, in load_lyco assert False, f'Bad Lyco layer name: {key_diffusers} - must end in lyco_up.weight, lyco_down.weight or alpha' AssertionError: Bad Lyco layer name: lora_te_text_model_encoder_layers_0_mlp_fc1.diff_b - must end in lyco_up.weight, lyco_down.weight or alphaIs your web-ui up to date?
Since the update for supporting full module lycoris is pretty recent, it's probably an error related to using an sightly outdated install of the web-ui. Try updating it if you can or do a fresh install inside another folder.
I'm also getting the same issue like this. doesnt matter what weight i use it it's the same result unless its 0.
@jimtheman Your webui must be up to date and you must delete the older lycoris extension from older installations. Since it's a new type of lycoris and the creator pushed the inference code to auto1111, you will probably be fine with just using "git pull" to update your stuff
@ckmlai I am using Vlad's fork and at commit df9c009 which is the most recent at main branch, but also getting this error.
Hey do you have the dataset and the pictures available to download?
Sorry but I can't share the dataset since that could count as redistributing the images. You can build your own using tools like grabber and an auto tagger pretty easily. It's just a matter of curation after that
Where can one obtain the PenisDetector model for ADetailer?
https://civitai.com/models/132388?modelVersionId=149639
Added to the suggested resources
@ckmlai Brilliant! TY for the assistance. I have been going deep and enjoying the model/lycoris :)
@Rhobu I'm glad you're liking it! Have fun!
Great lyco, but i'm having trouble with the dylora version.
Does the dylora version also work with the Additional-Networks extension? When I load it I get a wall of text something about "Incompatible keys, missing keys"
Additional-Networks extension is deprecated and probably wont work with most of the lycoris modules that got updated, dylora included. The recommended way of using it nowadays would be updating the webui, getting rid of the deprecated lycoris and aditional networks extensions and then calling it through the prompt syntax <lora:FutanariConcept_Dylora_alpha_v1-14-000014:1>
Decent model, but it happens to really really like making balls, like it reallly really loves big fat balls and no penis, get that penis out of here no penis just balls. Maybe depends on what you're tryna get tho