https://civitai.com/models/3671?modelVersionId=1623867

Use e621 tags (no underscore), Artist tag very effective in YiffyMix.

GridList Species(v60)/Artist(v61/v52) update!! & LoRAs (SDXL)/samples/wildcards

Recommend Artist List for new user & comfyUI workflow

YiffyMix doesn't need Pony score tags, Don't use SD1.5 vae in SDXL, you will get fried image. Example Setting

Setting SDXL (SDXL-lightning & NoobXL)

Steps = 12~24

Sampler = "DDPM", "Euler A SGMUniform", "Euler SGMUniform"

CFG scale = 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

LoRA Training

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

unet_lr = 0.0001

text_encoder_lr = 0.00005

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"

workflow demo

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,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.

v6.0 [2D,3D,res:896~1536] ※NoobXL eps version (not v-pred)

More character better sex pose, limited and uncontrollable style (mostlly anime style).

v6.1 [2D,3D,Realistic,res:896~1536] ※NoobXL eps version (not v-pred).

More realistic detail, reduce anime style, fix flat and boring background.

v6.1a-RE [2D,3D,Realistic,res:896~1536] ※NoobXL realistic enhanced (RE) version.

Same as v61 but adjust average style to simi-realistic. 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:

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 v5x:

by Mandy Disher, by Wim Wenders, by Robert Rauschenberg, [by Fossa666::0.65],

ultra realistic, photorealism, photograph,

Prompt SDXL v6x-Noob:

[3d (artwork):(ultra realistic, photorealism, photograph:1.35):0.35]

Negative prompt SDXL:

sketch, manga, vector, line art, toony

Some SD tricks using a1111 [a:b:value] script prompt:

1.High details increase

[:some style or artist:0.15]

Let first 10%~20% steps free, then style will create on high detail base.

2.Avoid character pose affected by artist or background

[:artist or background prompt:0.2]

Skipping first 20% steps can avoid this.

3."A artist character" + "B artist style"

[A artist:B artist:0.35]

Most base concept is done in first 30%~50% steps, last steps only change style.