Use e621 tags (no underscore), Artist tag very effective in YiffyMix.
GridList Species/Artist(v64) update!! & LoRAs (SDXL)/samples/wildcards
Recommend Artist tags (NoobXL) & comfyUI workflow.
Example Setting (Use recommended sampler to get correct quality)
Setting SDXL (SDXL-lightning & NoobXL)
Steps = 12~24
Sampler = "DDPM", "Euler A SGMUniform", "Euler SGMUniform"
CFG scale = 3~4
Negative embeddings SDXL = ac-neg1, ac-neg2 (You don't really need this)
Postive LoRA SDXL = SeaArt Quality Tags LoRA (You don't really need this)
Stop at CLIP layers = 2
Setting SD 1.5 + vpred
Steps = 30~40
Sampler = "DPM++ 2M Karras", "DPM++ SDE Karras", "DDIM", "UniPC"
CFG scale = 6~8
Negative embeddings = deformity_v6, bwu [SD-WebUI\embeddings]
Stop at CLIP layers = 1
SD VAE = kl-f8-anime2, Furception [SD-WebUI\models\VAE]
Hires. fix
Hires steps = Steps * Denoising strength
Denoising strength = 0.25
Hires upscaler = 4x-UltraMix_Smooth [SD-WebUI\models\ESRGAN]
ControlNet
ControlNet = softedge_hed, control_v11p_sd15_softedge
ControlNet SDXL = softedge_hed, sdxlsoftedge-dexined, noobai-xl-controlnet
ControlNet Weight = 0.35~0.5
ControlNet Pixel Perfect = true
Wan 2.2 ComfyUI Animeted [workflow]
model = wan2.2_ti2v_5B_fp16
vae = wan2.2_vae
lora (turbo) = lora_wan2.2_ti2v_5B_turbo_lora_rank_64_fp16
lora (furry-nsfw) = wan2.2-5B_furry-nsfw-v2.0-e83
lora (livewallpaper) = wan2.2-5B_livewallpaper-720p
sampler = steps:4, cfg:1, sampler:"eular_ancestral", schedule:"sgm_uniform"
SD WebUI
LoRA Training SDXL
imgs count = 15~50
total steps = epoch * imgs count * folder loop = 3000~4500
network_dim = 64
network_alpha = 128 (SDXL) \ 16 (Noob)
learning_rate = 0.0002~0.0005
unet_lr = 0.0001 #learning_rate/2
text_encoder_lr = 0.00005 #learning_rate/4
lr_scheduler = "cosine_with_restarts"
mixed_precision = "bf16"
optimizer_type = "Adafactor"
optimizer_args = [ "scale_parameter=False", "relative_step=False", "warmup_init=False", ]
YiffyMix v4x V-pred Setting
# YiffyMix v4x A1111 SD-WebUI or Forge V-pred Setting
1.Download config file ".yaml" paste next to the model.
2.Raname ".yaml" same as model name. ( check the ".yaml" has [parameterization: "v"] line )
3.Restart SD-WebUI ( if config fails to load, the model just generate noise )
# YiffyMix v4x ComfyUI or StableSwarmUI V-pred Setting
Add node "ModelSamplingDiscrete", Sampling = "v_prediction"
# ComfyUI V-pred Setting (old version)
1.Copy config ".yaml" to [ComfyUI\models\configs] and refresh ComfyUI
2."Load Checkpoint (With Config)" [Right Click\AddNode\advanced\model_merging]
workflow:[Load Checkpoint (With Config)]-[KSampler]-[VAE Decode]-[Save Image]
# v-pred mode troubleshoot
If you use new version webui-forge and failed detect v-pred model.
Try update webui-forge (click update.bat).
When loading v-pred model, you will see this line in cmd console:
left over keys: dict_keys(['v_pred'])
# v4.x some time will get little fried issue image in this case
Use "Dynamic Prompts with __wildcards__ prompts" and "batch size > 1"
Just generate again with same prompts with parament, it will return normal.
Version Info
v1.x [2D,512~768] old model, unstable, low resolution
v2.x [2D,512~896] e621 dataset + 30~40% SD5 dataset
v3.0 [2D,3D,512~1088] large dataset then v2.x version, can do 2D, 3D
v3.1 [2D,3D,Real,512~1088]
more realistic, but loss some concept (e621 tag count lower 1000)
v3.2 [2D,3D,Real,512~1088]
unstable version, use SNR version FluffyRock, more noise detail
v3.3 [2D,3D,Real,512~1088]
stable version, more detail, more sensitive to prompts
v3.4 [2D,3D,Real,512~1088] ※include Fluffy Rock Quality Tags-LoRA
stable version, more detail, clear result, reduce some noise (like bush,pattern)
v3.5 [2D,3D,Real,512~1088]
unstable version, contrast & detailed enhance
v3.6 [2D,3D,Real,512~1088]
stable version, more sensitive to e621 tags
v3.7 [2D,3D,Real,512~1088]
stable version, reduce noise overactivity, fix blurry eyes and finger error, fix failed background depth
v4.0 [2D,3D,Real,512~1088]
v-pred version, remix from EasyFluff
accuracy anatomy and style with fewer prompt,
little dim blue average color with smooth noise, weakly negative prompt issue
v4.1 [2D,3D,Real,512~1088]
v-pred version, color and low contrast fix, reduced realistic noise.
v4.2 [2D,3D,Real,512~1088]
v-pred version, more contrast and detail, yelow issue.
if you feel too fried use Rescale CFG =0.35
v4.3 [2D,3D,Real,512~1088]
v-pred version, clear artist style, fix most yellow/brown issue
the version doesn't need CFG Rescale
v4.4 [2D,3D,Real,512~1088]
v-pred version, no more yellow/brown issue.
the version doesn't need CFG Rescale
v5.0 [2D,3D,Real,896~1536]
SDXL-lightning version, base on Compassmix XL.
v5.1 [2D,3D,Real,896~1536]
SDXL-lightning version, more e621 dataset, lower human face, better NSFW stuff.
v5.2 [2D,3D,Real,896~1536]
SDXL-lightning version, increase average quality. Little unstable than v51 but more creative.
v6.0 [2D,3D,res:896~1536]
More character better sex pose, limited and uncontrollable style (mostlly anime style).
v6.1 [2D,3D,Real,896~1536]
More realistic detail, reduce anime style, fix flat and boring background.
v6.1a-RE [2D,3D,Real,896~1536]
Same as v61 but adjust average style to simi-realistic.
v6.2 [2D,3D,Real,896~1536]
more effective prompt, keep style also with good realistic detail, saturation down little bit.
v6.3 [2D,3D,Real,896~1536]
Detail(noise) level between v62 and v61, upgrade character/artist accuracy.
v6.4 [2D,3D,Real,896~1536]
Upgrade light quality and average detail.
Note about NoobXL to create stable furry (v6x):
use "furry" tag in propmt can let AI create furry not human.
use "no human" tag in propmt can avoid NoobXL model add human and reduce anthro affect (more original style).
use "anime style" in negative propmt can reduce classic booru style and more realistic.
Some SD prompt trick:
Combine two character:
characterA \(characterB\)
Avoid tag bleeding:
(chain:0)-link fence
(cowboy:0) shot
high (collar:0)
Multi-tag combine, enhance and reduce token use:
from side + side view = from side view
crossed legs + legs up = crossed legs up
Basic Style
Negative Prompt SD1.5
unusual anatomy, mutilated, malformed, watermark,
amputee, mosaic censorship, sketch, monochrome
Negative Prompt SDXL
malformed, worst quality, bad quality, signature, text, url
3D Artwork Style
Prompt v5x: blender \(software\), ray tracing, 3d, unreal engine
Photorealistic Style SDXL
Prompt v5x:
by Mandy Disher, by Wim Wenders, by Robert Rauschenberg, [by Fossa666::0.65],
ultra realistic, photorealism, photograph
Negative prompt v5x: sketch, manga, vector, line art, toony
Prompt v6x: film photography, photorealistic, film grain
Negative prompt v6x: anime style, vibrant, pastel
Photorealistic Style SD1.5
Prompt sd15: [:photorealistic, analog style, realistic, photorealism:0.5]
Negative prompt sd15: [:bwu:0.5]
Recommend Refiner: IndigoFurryMix v110-Realistic Switch at 0.5
Description
Recipes v21:
preYM2a = (FluffyRock-e16o1+Zeipher F111-SD4) * diff:1.0
YiffyMix v21 = preYM2a + Deliberate v2 0.4 + Fluffusion-e15 0.35 + CrossKemono2.5 * 0.1
FAQ
Comments (30)
maybe 2.1 should already be FluffyMix?
this guy needs donations, he is helping us all and doing god's work.
Anyone else having trouble making images with fisting? Maybe it just didn't have enough training data? If anyone's gotten any good images, let me know what tags you used.
I think you might need to use additional LORAs, like this, since this model seems to be not trained to any other poses, rather than standart penetration.
Hello, I wanted to ask about how you would go about triggering specific tags that have to deal with parenthesis ie:
gloves (marking)
I assumed that gloves\(marking\) would work, but I have tried it with several parenthesis tags, and they seem to not trigger at all
I am not sure what the proper calling is for these sorts of tags, but I would really like to be able to use them at some point
Can you do a Fluffusion E20 merge pls?
I think this has too much of Fluffyrock in it, it can barely handle Fluffusion tags. Really this model would be better if it used more Fluffusion than Fluffyrock
I enjoy this model, but it does NOT like teeth/fangs/mouths in general. If that can be addressed then this would be a near perfect checkpoint.
Please upload the individuals somewhere other than MEGA, the free file limit is too small to fully download the package, or even one folder at a time.
i agree but it toke me 1 full day and a hafe to download them all
How do I use the AI? Can I download it and use it locally instead of using random websites which need payment?
I recommend you to search in youtube a tutorial on how to use stable diffusion.
i recommend this one https://www.youtube.com/watch?v=3cvP7yJotUM
is it better to use a lora or sex position themed tags from e621?
Use both. That models is pretty basic on poses, and can produce only basic poses, such as missionary or cowgirl.
Hello, I was wondering how this model differs from the one being run on mage.space? I have tried to recreate some of my mage images locally, but even when I use the same exact settings (prompt, negative prompt, seed, dimensions, guidance scale, and steps), I get different results.
This is my setting in SD-WebUI v1.2.1:
Stop At last layers of CLIP model = 0
Eta noise seed delta = 0
Use old emphasis implementation = false
Enable quantization in K samplers = true
webui-user.bat:
COMMANDLINE_ARGS=--opt-sdp-no-mem-attention
If result still different...I don't know where the problem is
sampling method matters for end results, and mage dosent let anyone know what sampling method theyre using.
So... like... this is a furry model of all thing and I think it had more care put into it than 98% of the models out there. What ever setting, action and pose you enter into your prompt, it makes it. Anything from wholesome to straight up hentai and everything in between. Also, why can this thing make a verity of posable paws and most models can't make a normal hand? Why is one of the best made model I've found for freaking furries! I'm so amazed and infuriated by this thing. I want to hate it and delete it but I can't stop using it! Damit!!!!
Update/Edit: I will never be able to look at umbreon the same way again.
I know exactly zero about furry stuff so can someone please share a few cute characters that would be In here? The only one I could think of was Judy hopps because I say zootopia well scrolling through Disney plus this morning.
@Deforest "CATS, he said eventually. CATS ARE NICE"
@Deforest if you go in to hes https://mega.nz/folder/UBxDgIyL#K9NJtrWTcvEQtoTl508KiA there is a lot of Lora files of cute Chibi animals and others stuff like wildcards to artstyle and more
@champagne1 Thank you!
@Deforest np
I would just like to say that this is, hands down, the best SD model I have used so far. Excellent job.
I'm a newbie at this, but I have tried like 20 different models, several high rated, and it takes a HUGE amount of tweaking to make even simple scenes look good and you never understand what the hell is going on.
But with this one, for simple scenes (one subject, one pose, simple background and lighting/detail) you just add a few tags and boom, nice looking furry girl comes out. Strongly recommend that you peruse the gallery to fish out some prompt ideas, but this model already produces some good stuff by default. It's really great!
This model is amazing - It's especially amazing for generating art for the D&D campaign I run.
Tabaxi rogue? Piece of cake.
Kobold sidekick? Just like I ordered.
Tiefling blacksmith? Instant success.
Minotaur tavern owner? Poof, there he is.
The possibilities truly are endless. Thank you so much for producing this!
when you try a human x anthro, my human character's facial features are always disfigured and low quality. I use the "human" tag, the anthro/furry character is always high res and clear
I've been trying to do hybrids but I haven't had any luck either. If you do come up with something that works I'd love to know.
@Deforest i am just trying to make an image with a male/female duo. One anthro male and one human female. the anthro is perfectly detailed, the human is deformed and has poor clarity. 2.2 is out so will give that a shot!
A1111 has issues rendering multiple characters without prompts bleeding into each other. You might want to look up some videos on the Latent Couple extension to see if that can help you out.