Description
Use e621 tags (no underscore), Artist tag very effective in YiffyMix.
Species/Artists grid list (update v51) & Furry LoRAs/samples/wildcards
VAE:WD-KL-F8-Anime2, Furception correct contrast and noise reduction [Settings\Stable Diffusion\SD VAE]
ClipSkip:Stop at CLIP layers=1 (SD=1, NAI=2, SDXL=2) [Settings\Stable Diffusion\Clip skip]
Recommend Artist List for new user & comfyUI workflow
YiffyMix v5x SDXL-lightning setting
YiffyMix v5x doesn't need PonyXL score tags.
Don't use SD1.5 vae in SDXL, you will get fried image.
use setting [steps=12~24, cfg=4~6]
recommend sampler :
smooth (realistic style) : ["DDPM", "Euler A Turbo", "Euler A SGMUniform"]
detail and balance (anime style) : ["Euler", "Euler SGMUniform"]
high detail and contrast: ["DPM++ 2M SDE SGMUniform"]
SDXL quality tags LoRA (trigger words: prompt=best quality, neg_prompt=worst quality)
some issue in SDXL:
some sampler has goosebumps noise problem.
sometime character nose, eyes, shape tip has little fuzzy noise.
in A1111 emphasis parentheses may gen empty noise image
(try change prompts order or remove parentheses).
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.
Example Setting
Txt2img Setting
Steps = 30~40
Sampler = DPM++ 2M Karras, DPM++ SDE Karras, DDIM, UniPC
CFG scale = 6~8
Negative embeddings = deformity_v6, bwu [SD-WebUI\embeddings]
Negative embeddings SDXL = ac-neg1, ac-neg2 [SD-WebUI\embeddings]
Hires. fix
Hires steps = 15
Denoising strength = 0.45~0.5
Hires upscaler = 4x-UltraMix_Smooth [SD-WebUI\models\ESRGAN]
Img2img Resize
Scale to = 1.5~2.0
Denoising strength = 0.45~0.5
ControlNet0 = softedge_hed, control_v11p_sd15_softedge
ControlNet0 Weight = 0.4~0.5
ControlNet0 Pixel Perfect = true
ControlNet1 = Reference
ControlNet1 Weight = 0.2~0.3
ControlNet1 Pixel Perfect = true
SD Setting
Stop at CLIP layers = 1
Eta noise seed delta = 0
SD VAE = kl-f8-anime2, Furception [SD-WebUI\models\VAE]
Txt2img Animated Diff ※no "BREAK", tokens < 75
Steps = 30~50
Sampler = DDIM
CFG = 10~20
ImageSize = 512~768 ※large image less motion
Number of frames = 10~14
Negative Prompt v2
unusual anatomy, mutilated, malformed, watermark,
amputee, mosaic censorship, sketch, monochrome
Negative Prompt SDXL
malformed, worst quality, bad quality
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,Realistic,res:512~1088,VAE Baked]
stable version, reduce noise overactivity, fix blurry eyes and finger error, fix failed background depth
v4.0 [2D,3D,Real,512~1088,VAE Baked]
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,VAE Baked]
v-pred version, color and low contrast fix, reduced realistic noise.
v4.2 [2D,3D,Real,512~1088,VAE Baked]
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,VAE Baked]
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,VAE Baked]
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,Realistic,res:896~1536]
SDXL-lightning version, increase average quality. Little unstable than v51 but more creative.
3D Artwork Style
Prompt:
masterpiece, best quality, light, 4k, 2k,
blender \(software\), ray tracing, 3d, unreal engine
Photorealistic Style
Prompt:
[:photorealistic, analog style, realistic, photorealism:0.5]
Negative prompt:
[:bwu:0.5]
Recommend Refiner:
IndigoFurryMix v110-Realistic Switch at 0.5
Prompt SDXL:
masterpiece, best quality, ultra realistic, 4k, 2k, high detail, subsurface scattering,
film photography, sharp focus, RAW photo, photorealistic, photorealism
Recipes v52:
partA = Compassmix XL + Boltning v1.0 * 0.35
partB = (partA + BananaStrike XL - SDXL Lightning 4 step) * trainDiff:0.25
YiffyMix v52 = (partB + Compassmix XL - SDXL Lightning 4 step) * trainDiff:0.25