Text-to-seggs is finally here! Say NO to clunky controlnets. With this motion module and animeDiff you can produce 1 clip in less than 30 seconds.
Fresh from YoinkoorLab, trained on the base motion modules using hand picked high quality data.
This motion module uses the newly released 1.5 v2 motion module as a base.
6/10/2023 Version Update:
We have achieved a state of the art (SOTA) text-to-seggs motion module.
What this version offers:
Better generalizability, Insane details, good motion for realistic models.
This mm is tuned to use for yoinkooranime
-->Join the discord<<- We have an AnimateDiff bot, you can try AD without installing anything.
Whats coming: Making motion better on anime models.
18/9/2023 Version Update:
( ͡° ͜ʖ ͡°)( ͡° ͜ʖ ͡°)( ͡° ͜ʖ ͡°)( ͡° ͜ʖ ͡°)
-->Join the discord<<- We have an AnimateDiff bot, you can try AD without installing anything.
( ͡° ͜ʖ ͡°)( ͡° ͜ʖ ͡°)( ͡° ͜ʖ ͡°)( ͡° ͜ʖ ͡°)
16/9/2023 Version Update:
Many of our users were using vertical aspect ratios. And so,
Introducing: GODMODE
The best motion module for your *ahem* pov vertical clips.
How to use
Use whichever animeDiff UI exention that has updated to support v2. Comfyui is the best.
Do NOT use anime models, it wont have much motion. its because the new base cant produce it for some reason.
If you're not getting good results, change the sampler, or checkpoint (Movement is very reliant on the diffusion model). Also, use simple VAEs that don't affect the saturation that much.
Animediff NSFW discord server:
https://discord.gg/FpDbSkAe7m<----- join to share feedback and learn from others.
Animediff settings
You should use 512 by 512 or 768 by 512 (landscape) at 16 context length.
Prompt guide:
Use your favourite SD keywords like: Detailed face, beautiful face etc.
Special words to get maximum SEGGGS:
girl, naked, pov, sex, cowgirl position,penis, vaginal sex,face, vertical
Negative prompt:
watermark, signature, bad quality, worst quality
Description
Very good mm, no artifacts good detail and movements
FAQ
Comments (24)
698ce4aa7755b09affd79d1b84fcb883d8af35fda5872dd2170d1f17c1e11e0c
hash for godmodev2.0
I have broken images for the 2.0 version. :(
join discord for help
where do i put these motion models file wise? is this for use with animatediff?
sd.webui\webui\extensions\sd-webui-animatediff\model yes its for animatediff
where do i put these motion models file wise? is this for use with animatediff?
1 Ensure that you've installed the AnimateDiff Extension
2 Download the Motion Module
3 Place the file inside the extensions/sd-webui-animatediff/model/ folder
add below to mm_zoo.json in animatediff folder to use. suggested 30 steps + 40 frames/8 fps to test
"698ce4aa7755b09affd79d1b84fcb883d8af35fda5872dd2170d1f17c1e11e0c": {
"name": "yoinkoorlabsNSFWMotion_godmodev20.ckpt",
"arch": 2 }
What does this added code do? Thanks!
ah yes the horny I was looking for :)
Discord invite is acting like it is broken. It says "unable to accept invite". -.-
arYgr2WF try this
What sampler/steps etc. do you recommend when you use this? Thanks!
is it not possible to make those with .safetensor ?
So I'm a complete noob when it comes to ComfyUI--how do I use this file? Do I upload it somewhere? lol
in comfyui custom nodes->animateddiff->models
@Yoinkoor Oh so within the zip file? (It's a zip file eh?)
Can you make this for other positions like blowjob or handjob?
I get this error when I try to run it, any idea what I did wrong?
File "C:\Users\user\Documents\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\model_injection.py", line 207, in load_motion_module
load_motion_lora_as_patches(motion_model, lora)
File "C:\Users\user\Documents\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\model_injection.py", line 176, in load_motion_lora_as_patches
patches[model_key] = (torch.mm(weight_up, weight_down),)
how to use with A1111? i know nothing about comfy. node stuff just gives me a headache. already a pain in the ass in my 3d software stuff
Is it possible to get blowjob animation from this?
I'm using ForgeUI now because Comfy is too complicated for me. Can I put the model into SVD model folder? Forge comes together with a lot of pre-installed things, some of which are not working with A1111
Hi. Hope someone can help. I have added extension in A111. Downloaded motion modules and put them in WebUI\stable-diffusion-webui\extensions\sd-webui-animatediff\model. I have clicked AnimateDiff drop down, loaded a motion module and enabled AnimateDiff - even on very low frame # and FPS - all I am getting is a PNG image. What am I missing - big thanks to anyone who can help.