IL v2.3 : New version, more flexibility. Better than IL v1
This version don't have a baked in VAE. I recommend to use SDXL VAE
Please consider supporting me so I can continue to make more models --> https://www.patreon.com/BB95FurryMix
Don't forget to join the Furry Diffusion discord server --> https://discord.gg/furrydiffusion
Since v3, this model uses e621 tags.
This model is a mix of various furry models.
It's doing well on generating photorealistic male and female anthro, SFW and NSFW.
I HIGHLY recommend to use Hires Fix to have better results
Below is an example prompt for the v7/v6/v5/v4/v3/v2.
Positive:
anthro (white wolf), male, adult, muscular, veiny muscles, shorts, tail, (realistic fur, detailed fur texture:1.2), detailed background, outside background, photorealistic, hyperrealistic, ultradetailed,
Negative:
I recommend to use deformityv6 and boring_e621_fluffyrock_v4, you can add bad-hands-v5 if you want
Settings 1.5 :
Steps: 30-150
Sampler: DPM++ 3M Karras, DDIM, UniPC or Euler A
CFG scale: 7-14
Size: from 512x512 to 750x750 (only v4/v5/v6/v7/v8/v9), up to 900x900 for v10/v11/v12
Denoising strength: 0.6
Clip skip: 1
Hires upscale: 2
Hires steps: 30-150
Hires upscaler: Latent (nearest)
Settings XL :
Steps: Below 30
Sampler: Euler A
CFG scale: 3-6
Size: 1024x1024
Denoising strength: 0.2
Clip skip: 1
Hires upscale: 2
Hires steps: Below 30
Hires upscaler: Remacri
Description
This version has a more realistic and better fur, better clothes, better NSFW !
Rarely, can generate weird things
This version has a baked in VAE.
FAQ
Comments (21)
So what are these "weird things" it generates? Nothing I need to worry about I hope.
No ! just sometimes, you have some malformities
Is there a list available of working tags?
You can use the one from FluffyRock
@Bumblebee95 thanks, they seem to be working good.
how to apply the update?
i need to unninstall and install or another method more easy?
yes, i don´t know any ***** :c
You just need to add the model into SD/models/checkpoint
And after that, you just need to reload your webui and change the model on the top of the page on the left
then... can i unistall my actual version 4.0 (without VAE) and install the last version?
5gb D:
@sitarhero You just have to delete the old one if you want
@Bumblebee95 hey sir can u invite me to the discord :c
"woops unable to accept the invitation" :/
@sitarhero https://discord.gg/furrydiffusion
@Bumblebee95 "woops, unable to accept the invitation" again...
why? :c
@sitarhero I don't know, the link works for me
@Bumblebee95 can i add u on discord? :c
@sitarhero give me your discord username, I will add you
COOL! Its a realy great job. We waiting for updates for penises (feline - lion, panther; bovine - bull, bison, etc). Now its not real((( But it is really need!
This is seriously my new favorite model, not for furries, but for aliens, but also for vore. just wish it could do humans a bit better. I hope theres an XL version. Guess we need a fluffyrock XL first.
How do you get it to work with vore?
@bcgriffin14611 use fluffy rock tags, (e621), (((Female Pred ))), (((hyper pregnancy))), (((hyper belly))), (((struggling prey))), and (((same size vore))) all work, its not good at doing swallowing though.
@Taco360 sorry for the noob question but I've seen people refer to the fluffyrock tags, are they talking about the "fluffyrock quality tags" or the "Pre-3M Autocomplete" files? I assume the later but im still a bit confused at what this actually does. Does it just help you remember/enter tags and show aliases, or does its inclusion in webui also affect how images are generated directly? Thanks!
I ask the author to lay out the inpaint model. And just in case, I'll post instructions on how to do it myself.
How to create an inpaint model.
Download the any model
Download the basic inpainting model ( https://huggingface.co/runwayml/stable-diffusion-inpainting )
Download the model "v1-5-pruned-emaonly.ckpt " ( https://huggingface.co/runwayml/stable-diffusion-v1-5 )
Go to the Checkpoint merger tab in Stable Diffusion.
In model "A" put - "sd-1.5-inpainting", in model "B" put "your model", in model "C" put "v1-5-pruned-emaonly.ckpt"
"Multiplier (M) - set to 0 to get model A" = 1
Interpolation Method - add difference
Check the box on float16
CLICK "MERGE"
Rename the resulting model and insert necessarily -inpainting.
HERE ARE THE NORMS: sd-1.5-inpainting.safetensors
HERE IS NOT THE NORM: sd-1.5inpainting.safetensors