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 v32:
preYM3 = (Fluffusion-e20+Zeipher F111-SD4) diff:1.0 + Furraffinity-e21 0.35 + Furtastic v2 * 0.35
partA = preYM3 + ReV Animated v1.2.2 * 0.4
partB = preYM3 + DarkSushiMix-Darker * 0.4
partC = (partA + partB) 0.5 + FluffyRock-e85-snr-e58 0.45
partD = (partC + IndigoFurryMix_v35 Realistic - YiffyMix v22) * diff:0.35
YiffyMix v32 = partD + YiffyMix v22 * 0.4
FAQ
Comments (28)
I'm getting way too many fingers and toes with V32, especially compared to the previous version which feels more stable. I think this might need one of those textual inversion thingies to help fix that.
For LoRA training, which version of Fluffyrock is best to use for Yiffymix compatibility?
a suggestion to the creator, dont take the photorealistic route with this mix, as its looks good as it is now, as i like the in between style 2.5d and the vae makes it even better with the right amout for shading, i use this mixed with other 2d furry models
I agree, we already have BB95 Furry Mix for realistic stuff and that's hard to beat. Also the "realistic" elements clash with the cartoony elements and makes things look rather underwhelming compared to the V31 version which is both more adaptable and more stable.
It's just prompts illusion.
Because I added "3D" and "photorealistic" enhance prompt in sample images.
If you exclude this part or set lower weight, you will get more regular 2D art.
@chilon249 , you can use both 2d, 2.5d with all of his models
i am hoping for more focus on photorealism, yiffmix is my preferred choice because of it's high compatibility with e621 tags.
I am hoping we can get some realism styled generations like the Newdawn/furtastic furry model
Same! I like this semi-2D/3D style, it has that unique aesthetic and this is what sets it apart. It gives the results a game-like, stylized and expressive, dynamic look. The more photorealistic the style is, the more boring, stiff and mundane it looks.
i really like how this model is capable of using different author styles with perfect fit, photorealism models is actually kinda boring like conveyor anime-like arts with small differences,
its kinda surprising how this model capable of understanding long prompts like "black_fur, green_eyes, round_glasses, by $authorname" with good results
This is a very good mod, I have drawn many works with it, thank you very much to the author
In V32 The "body" prompt tries to makes naked body. The v31 looks like more stable for me now
In V32 The "body" prompt tries to makes naked body. The v31 looks like more stable for me now
V32 seems to stuggle more with the "Countershading" prompt that V3, espescially when the color is described
I'm not getting the VAE through your link. Can you give me the name?
Are you going to make a version for SDXL 1.0?
Probably need to wait.
Until furry base model [FluffyRock and Fluffusion] update to SDXL stable version.
@chilon249 I can't wait to see what Yiffymix SDXL looks like!!!
@chilon249 I can't wait to see it when it does I love using YiffyMix
Hey I was gonna ask that! lol but yeah I wish there will be that unless it works for Base and Refiner too or just one for base idk. hah
Can't wait to see sdxl of this
This is good, but I wonder about something:
In the description, it says that e621 artist tags work really well. Does that apply to art-related tags like muscular or anything NSFW as well?
Any e621 tags will work.
You can use "e621-prompt" extension to easily get tags.
Do you recommend using the Boring_e621_v4 or the fluffy rock version for this model?
Subjective opinion:
I use boring_e621_v4 more often.
But according to the sensations, some prompts work better on one, others on the other, and still others - without them at all. Well, you can't guess.
Does this model have anatomically correct canine and equine vaginas and hyaenidae pseudo-penises?
Why don't you answer me? I need an answer
@nsfwpersonalai ANSWER HIM MAN!!!
Yes it does, you have to use ([insert species and genital here]:1.3) so an example would be (equine pussy:1.3) the 1.3 seems to be the most stable I've found, also prompting artists that utilize feral anatomy helps. Another tip is if you're using equines as an option adding "winking" or "vaginal wink" helps in additions if you add too many feral prompts your results start to get wonky with weird hoof/paw hand hybrids as well as funky looking genitalia.