(Generation on CivitAI only works with the Lora version: https://civarchive.com/models/2737606/animadrones-v1-lora )
The Only Full Murder Drones Finetune
(On CivitAI)
Trained on more than 4000 images, this Full Finetune achieves unparalleled generalization across everything that makes Disassembly Drones and Worker Drones destinct.
While I scraped literally every booru and image site, the training data has been processed down to only a few thousand images, with the best and most coherent asthetics and compositions. This theoretically means that every character in the entire show that has gotten any kind of fanart is in the dataset. Buuuut in reality not everything ever is posted to the big (or small) boorus.
Overall the distribution of the characters is wildly unbalanced, meaning: Very good at Uzi, V, J; Less good at Cyn and N and pretty bad at everything else. But with a specific enough prompt you can certainly bring every character from the Murder Drones universe on the canvas.
I'm ngl this is a NSFW model first and foremost, so be warned!
Please leave a like and a comment if you enjoy my models!
v1.9
Better character consistency and prompt following
The model can generate many characters at once. Without mixups!
If mixups ocure, specify the hairstyle of the characters and that should give perfect accuracy.
A little less freedom with the artstyle
Best performance with a two stage workflow. You can get mine by downloading one of the example images.
v1.9: ComfyUI + "er_sde" or "res_2s" + sgm_uniform + CFG 4 + 30 steps
v1
Pretty good prompt following: Except it likes to mix up the topping and bottoming characters.
Sometimes this can be fixed by just changing the order of them in the prompt
Clothes arerelatively accurate, but you can change them to whatever you like
Best performance with a two stage workflow. You can get mine by downloading one of the example images.
It can do 3D, 2D and pretty much every other artstile Anima it self can do
v1: ComfyUI + "er_sde" + sgm_uniform + CFG 4 + 30 steps
Prompting:
Works best if you start the prompt with the character tag: SD-V, SD-J, UZIDOORMAN, CYN, etc
If a character isn't generated correctly, type more describing traits: SD-V -> SD-V with short white hair, robot
SD-N often gets mixed with J for some reason
Anima sometimes gives the drones human skin. Fix that by typing: robot
(Tbh "robot" should almost always be included)
The Model likes to forget the tail. Luckily you can remind it by typing: tail
This time tag-based prompts are king, but natural language works too in some extend.
Qwen3 is very flexible
Sometimes the negative prompt can mess things up. Keep it minimal!
Description
More training = More better?
FAQ
Comments (6)
So, dragging any of the images into comfyui only makes it give a bunch of errors and tell me to install several things. And after I do so, the errors are still there. Then, it says it can not actually detect the model (animadrones obviously) despite it being in the models folder
Check if AnimaDrones is in the diffusion_models subfolder, since it's only the DiT without text encoder or VAE.
The rest of the errors probably are just missing LoRAs. Highres-Aesthetic and the turbo LoRA are the important ones. BallsDeep is just for adjustic porn stuff.
Hope this helps.
@Chaosnet Even when it is there, the program acts like it is not, and it does not even let me point to where it is either. I think I will just stay out of comfyui. Nothing about it is "comfy" and things keep saying missing no matter how many times I click install or restart. Sad, since this model has more characters to use. But no need for sadness, some things are just not ideal. Thanks for the help
@NUMBERONERATEDSALESMAN97 I use Forge Neo for everything, except for video, which, like you, I have not found how to make ComfyUI work for video without giving me problems and constant node errors.
For ANIMA you don't need ComfyUI, just updated ForgeNeo. It works with ANIMA, with KREA2, etc. Don't complicate your life, use Forge Neo.
@MirandoPaCuenca I avoided comfyui specifically because I did not want to complicate things. However, I will say that I had not checked neo before now, so thanks for recommending.
@MirandoPaCuenca Thank you for the aid. NEO works fine.













