Model
Trends
.ai
Model
Trends
.ai
les meilleurs modèles d'IA open source
Exécuter en local
koji_v21.safetensors
1.99 GB · SafeTensor · fp16 · pruned
Les téléchargements sont servis par Civitai. Certains créateurs demandent d'abord une connexion à Civitai.
À propos de ce modèle
STABLE DIFFUSION 1.5 · Modèles de base
Créé par
Ikena
sur Civitai
Koji v2.1 by Ikena is a more SFW version of hassaku. A great choice to use when you like 's art style but would like to render something other than boobs. It still can generate NSFW if prompted. It was trained on Danbooru tags and reacts well to them. The author recommends using it with: "masterpiece" and "best quality" in positive "[(low quality, worst quality:1.4), monochrome, signature, text, logo]" in negative Use /parser:new /clipskip:2 and /sampler:dpm2m
Notes du créateur
Kojis goal are easy to archive high quality anime images. Model is trained on . My for everything related to anime models and art. If you'd like to support my work, you can do so at: , every bit helps and is truly appreciated! ____________________________________________________________ Supporters: Thanks to my supporters tamashiicolle, pttcot, SETI and Kodokuna _____________________________________________________ Using the model: Use mostly tags. No extra vae needed. For better promting on it, use this or . But instead of {}, use (), use (). Use "masterpiece" and "best quality" in positive, "worst quality" and "low quality" in negative. My negative ones are: (low quality, worst quality:1.4) with extra monochrome, signature, text or logo when needed. Use clip skip 2 with sampler DPM++ 2M Karras or DDIM. Don't use face restore and underscores _, type red eyes and not red_eyes. _____________________________________________________ : Every LoRA that is build to function on anyV3 or orangeMixes, works on koji too. Some can be found , or on civit by , or _____________________________________________________ Base model for koji is Black result fix (vae bug in web ui): Use --no-half-vae in your command line arguments I use a Eta noise seed delta of 31337 or 0, with a clip skip of 2 for the example images. Model quality mostly proved with sampler DDIM and DPM++ SDE Karras. I love DDIM the most (because it is the fastest for model testing).
29,611 téléchargements · 3,218 j'aime sur Civitai
SHA256
CADAE35D323EE7E3D5952496209B38CDD4F3BEFCA8E2D77F39D689A585F12CD5
ID de modèle ModelTrends.ai
#6190
Signaler le contenu
Rendus d'exemple
Prompts et réglages partagés par les personnes qui ont réalisé ces rendus sur Civitai. Choisissez un rendu pour voir comment il a été fait.
Réglages
Sampler
Restart
Étapes
16
Guidance
7
Seed
111679647
Taille
512x768
Clip skip
2
Prompt
<lora:SnootChallenge:1.0><lora:karylV1:0.9><lora:SadMadFaces:0.6> (masterpiece, highres, best quality:1.2), IncrsSnootChallenge, comic, 3koma, ADDBASE :o , karyl, low twintails, cat ears, hair bow, bangs, green eyes BREAK smiling, excited, karyl, low twintails, cat ears, hair bow, bangs, green eyes, BREAK (pov hands:1.4),(puffy cheeks, pout, pouting:1.3), (blush:1.2), mad, karyl, low twintails, cat ears, hair bow, bangs, green eyes, bare shoulders, brooch, hands on another's face
Prompt négatif
(low quality, worst quality:1.4), ADDBASE BREAK BREAK (smiling, hands on own face:1.4) (masterpiece, highres, best quality:1.2), IncrsSnootChallenge, comic, 3koma, ADDBASE :o , karyl, low twintails, cat ears, hair bow, bangs, green eyes ADDROW smiling, excited, karyl, low twintails, cat ears, hair bow, bangs, green eyes, ADDROW (pov hands:1.4),(puffy cheeks, pout, pouting:1.3), (blush:1.2), mad, karyl, low twintails, cat ears, hair bow, bangs, green eyes, bare shoulders, brooch, hands on another's face ADDBASE BREAK BREAK (smiling, hands on own face:1.4)
Réglages
Sampler
DPM++ 2M Karras
Étapes
20
Guidance
7
Seed
3568587889
Taille
512x776
Clip skip
2
Prompt
masterpiece, best quality, 1girl, yellow eyes, medium hair, stairs, cherry blossoms, temple, fox girl, detached sleeves, animal ears, happy, arms behind back,
Prompt négatif
(worst quality, low quality:1.4), tail,
Réglages
Sampler
DPM++ 2M Karras
Étapes
20
Guidance
8
Seed
3454595111
Taille
512x832
Clip skip
2
Prompt
masterpiece, best quality, 1girl, theme park, glowing, :3, cat ears, black hair, glowing, yellow eyes,
Prompt négatif
(worst quality, low quality:1.3)
Réglages
Sampler
DPM++ 2M
Étapes
24
Guidance
7
Seed
1292286979
Taille
512x512
Clip skip
2
Prompt
1girl,<lora:CrayonVT_v2_00010:1>,crayonvt,solo,portrait,simple background,upper body,shirt,yellow shirt,sample color shirt
Prompt négatif
text,blurry,low quality,bad anatomy,sketches,lowres,normal quality,monochrome,grayscale,worstquality,signature,watermark,NSFW,logo,cropped,bad proportions,out of focus,username,easynegative,fused fingers,too many fingers,extra legs,bad feet,cross-eyed,mutated hands and fingers,floating limbs,disfigured,long body,(fat:1.2),poorly drawn face,disconnected limbs,bad hands,long neck,skin blemishes,extra limb,missing fingers,malformed hands,malformed limbs,ugly,bad body,mutation,missing limb,poorly drawn hands,mutated,acnes,mutated hands,skin spots,extra arms,deformed,Multiple people
Réglages
Sampler
DPM++ 2M
Étapes
24
Guidance
7
Seed
3137363375
Taille
512x640
Clip skip
2
Prompt
1girl,<lora:CrayonVT_v2_00010:1>,crayonvt,virtual youtuber,solo,jewelry,blush,necklace,star \(symbol\),wallpaper,((wedding dress:1.4)),(veil:1.2),(white dress:1.2),crown,bridal,smile,ruanyi0263,((bridal veil:1.2)),bride,lace
Prompt négatif
text,blurry,low quality,bad anatomy,sketches,lowres,normal quality,monochrome,grayscale,worstquality,signature,watermark,NSFW,logo,cropped,bad proportions,out of focus,username,easynegative,fused fingers,too many fingers,extra legs,bad feet,cross-eyed,mutated hands and fingers,floating limbs,disfigured,long body,(fat:1.2),poorly drawn face,disconnected limbs,bad hands,long neck,skin blemishes,extra limb,missing fingers,malformed hands,malformed limbs,ugly,bad body,mutation,missing limb,poorly drawn hands,mutated,acnes,mutated hands,skin spots,extra arms,deformed,Multiple people
Modèles d'IA pour générer image, vidéo et texte
koji est un modèle de base pour la famille Stable Diffusion 1.5, référencé sur ModelTrends.ai, un catalogue en lecture seule de modèles d'IA open source pour l'image, la vidéo et le texte. Comparez-le aux autres modèles Stable Diffusion 1.5, consultez son score de chaleur pour suivre sa tendance et ouvrez-le sur PirateDiffusion ou BitVector pour l'essayer.
Parcourir par famille de modèles
Voir tous les modèles