SD

YiffyMix

#Furry

#Animal

#Fluffy

YiffyMix - AI Model cover image
Diunggah pada
17 Mei 2024, 22.42
Penggunaan
7.38k
Ulasan
Belum ada ulasan
Negatif

verybadimagenegative_v1.3, ng_deepnegative_v1_75t, (ugly face: 0.8), squint, sketches, (worst quality: 2), (low quality: 2), (normal quality: 2), low resolution, normal quality, ((monochrome)), ((grayscale)), skin spots, acne, skin defects, bad anatomy, deep negativity, turning away, {Several people}, low resolution, bad anatomy, very bad hands, text, error, missing fingers, extra digit, fewer digits, cropping, poor quality, low quality, normal quality, jpeg images, signature, watermark, user name, blurred, poorly drawn feet, cropped, poorly drawn hands, poorly drawn face, mutation, deformation, worse quality, low quality, normal quality, jpeg artifacts, signature, watermark, extra fingers, fewer digits, extra limbs, extra arms, extra legs

Izin
  • Allow image generation & sharing
  • Izinkan pengguna mengunduh model Anda
  • Penggunaan komersial

Deskripsi

Use e621 tags (no underscore), Artist tag very effective in YiffyMix v2/v3/v4Species/Artists grid list (update v43+v37) & Furry LoRAs/samples/wildcardsVAE: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) [Settings\Stable Diffusion\Clip skip]recommend YiffyMix v4.x use refiner [0.3~0.6] with other EPS (non-vpred) Model.Non vpred version recommend v34 & v36### v4.x is v-pred version, follow setting below #### 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 )# ComfyUI or StableSwarmUI V-pred Setting #Add node "ModelSamplingDiscrete", Sampling = "v_prediction" [Right Click\AddNode\advanced\model]workflow:[Load CheckPoint]-[ModelSamplingDiscrete]-[KSampler]-[VAE Decode]-[Save Image]# ComfyUI V-pred Setting (old version) #1.Copy config ".yaml" to [ComfyUI\models\configs] and refresh ComfyUI2."Load Checkpoint (With Config)" [Right Click\AddNode\advanced\model_merging]workflow:[Load Checkpoint (With Config)]-[KSampler]-[VAE Decode]-[Save Image]# Some problems #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 SettingTxt2img SettingSteps = 40~50Sampler = DPM++ 2M Karras, DPM++ SDE Karras, DDIM, UniPCCFG scale = 5~10Negative embeddings = deformity_v6, bwu ※[SD-WebUI\embeddings]Hires. fixHires steps = 15Denoising strength = 0.45~0.5Hires upscaler = 4x-UltraMix_Smooth ※[SD-WebUI\models\ESRGAN]Img2img ResizeScale to = 1.5~2.0Denoising strength = 0.45~0.5ControlNet0 = softedge_hed, control_v11p_sd15_softedgeControlNet0 Weight = 0.4~0.5ControlNet0 Pixel Perfect = trueControlNet1 = ReferenceControlNet1 Weight = 0.2~0.3ControlNet1 Pixel Perfect = trueSD SettingStop at CLIP layers = 1Eta noise seed delta = 0SD VAE = kl-f8-anime2 ※[SD-WebUI\models\VAE]Txt2img Animated Diff ※no "BREAK", tokens < 75Steps = 30~50Sampler = DDIMCFG = 10~20ImageSize = 512~768 ※large image less motionmodel = mm-Stabilized_mid, motionModel_v03-animeNumber of frames = 10~14Negative Prompt v2unusual anatomy, pixel (artwork), mutilated, malformed, watermark, amputee,restricted palette, mosaic censorship, deformity, sketch, unfinished, monochromeVersion Infov1.0 [2D,res:512~768]old model, unstable, low resolutionv2.x [2D,res:512~896]e621 dataset + 30~40% SD5 datasetv3.0 [2D,3D,res:512~1088]large dataset then v2.x version, can do 2D, 3Dv3.1 [2D,3D,Realistic,res:512~1088]more realistic, but loss some concept (e621 tag count lower 1000)v3.2 [2D,3D,Realistic,res:512~1088]unstable version, use SNR version FluffyRock, more noise detailv3.3 [2D,3D,Realistic,res:512~1088]stable version, more detail, more sensitive to promptsv3.4 [2D,3D,Realistic,res:512~1088] ※include Fluffy Rock Quality Tags-LoRAstable version, more detail, clear result, reduce some noise (like bush,pattern)v3.5 [2D,3D,Realistic,res:512~1088]unstable version, contrast & detailed enhancev3.6 [2D,3D,Realistic,res:512~1088]stable version, more sensitive to e621 tagsv3.7 [2D,3D,Realistic,res:512~1088,VAE Baked]stable version, reduce noise overactivity, fix blurry eyes and finger error, fix failed background depthv4.0 [2D,3D,Realistic,res:512~1088,VAE Baked]v-pred version, remix from EasyFluffaccuracy anatomy and style with fewer prompt,little dim blue average color with smooth noise, weakly negative prompt issuev4.1 [2D,3D,Realistic,res:512~1088,VAE Baked]v-pred version, color and low contrast fix, reduced realistic noise.v4.2 [2D,3D,Realistic,res:512~1088,VAE Baked]v-pred version, more contrast and detail, yelow issue.if you feel too fried use Rescale CFG =0.35(SD-Forge has builtin, LatentModifier Integrated/Rescale Cfg Phi)v4.3 [2D,3D,Realistic,res:512~1088,VAE Baked]v-pred version, clear artist style, fix most yellow/brown issuethe version doesn't need CFG Rescale# V-prediction model has following feature #Low-Rescale CFG : low frequency noise, cluster detail, high contrastSometimes less detail but smooth surface color and less mutation.High-Rescale CFG : high frequency noise, flat detail, low contrastmore detail can be shown, but not like EPS (non-vpred).You can see the visible halftone dot in "starry night sky" or "grassland".try "halftone background" to test it.3D Artwork StylePrompt:masterpiece, best quality, light, 4k, 2k, blender (software), ray tracing, 3d, unreal enginePhotorealistic StylePrompt:masterpiece, best quality, light, 4k, 2k, photography,photorealistic, analog style, realistic, photorealismNegative prompt:deformity_v6, bwu, high contrast, over saturated, glossy

Komentar