Model
Trends
.ai
Model
Trends
.ai
les meilleurs modèles d'IA open source
Exécuter en local
simpleIllustrious_vtowerSanctuary.safetensors
6.46 GB · SafeTensor · fp16 · pruned
Les téléchargements sont servis par Civitai. Certains créateurs demandent d'abord une connexion à Civitai.
AD
<simpleill-vtower-xl>
À propos de ce modèle
STABLE DIFFUSION XL 1.0 · Modèles de base
Créé par
naamakala
sur Civitai
by namakaala who writes: I liked two illustrious checkpoints shared here, SilvermoonMix01-Illustrious 1.1 and illustrious_pencil-XL 1.1, but had some minor gripes with the default styles of both, so I tried a very simple 50-50 merge between them and was pleasantly surprised by the result. Seems to have gotten rid of the lighting quirks of pencil and face quirks of silvermoon, though both of these might just have been skill issues on my part. I decided to share, since it's possible someone is looking for the same results as me. I've done very little testing overall, but this should still retain the prompt comprehension and artist and character knowledge of original Illustrious. I can recommend the following settings, but feel free to experiment and follow your heart: 28 steps 4 cfg euler a - align your steps positive: masterpiece, best quality, negative: bad anatomy, bad hands, error, extra digits, fewer digits, censor, sunlight, bright
Notes du créateur
vTower-Sanctuary is a 5050 weighted sum merge between and please check them out, maybe give them a thumbs up too if you like this merge :) The merge has a clean default style that changes a bit to match the subject matter, and it adheres pretty well to artist styles as most illustrious models do. The usual quality tags work and can affect the output a lot, so play around with them to see how they work and what puts out gens you like. Pretty decent range, not just a girl generator (though that way inclined unless otherwise prompted) and understands your intent pretty well. Recommended settings in the example images, just what I personally found to work well, feel free to play with these parameters too. v3? yeah, there -> v2.0 ? check the description -> I liked two illustrious checkpoints shared here, and but had some minor gripes with the default styles of both, so I tried a very simple 50-50 merge between them and was pleasantly surprised by the result. Seems to have gotten rid of the lighting quirks of pencil and face quirks of silvermoon, though both of these might just have been skill issues on my part. I decided to share, since it's possible someone is looking for the same results as me. I've done very little testing overall, but this should still retain the prompt comprehension and artist and character knowledge of original Illustrious. I can recommend the following settings, but feel free to experiment and follow your heart: 28 steps 4 cfg euler a - align your steps positive: masterpiece, best quality, negative: bad anatomy, bad hands, error, extra digits, fewer digits, censor, sunlight, bright Illustrious seems like a good step forward for local 'illustration' generation and I'm looking forward to many more merges and finetunes in the coming months.
762 téléchargements · 110 j'aime sur Civitai
SHA256
8CAFD4F01661235E2FDC090B7BA58861578B9F7BD19F8A23E3B83B8001D79E6E
ID de modèle ModelTrends.ai
#5217
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
Euler a
Étapes
20
Guidance
5
Seed
2536812159
Taille
1536x2304
Prompt
<lora:seated_sniper_cradle_ill_v3.5:0.8> 1girl, solo, sniper_cradle, scope, holding sniper rifle, front knee support, crossed arms, full body, aiming, looking away, aiming down, dynamic pose, tropical island, hand on arm, thumb grip, <lora:S4bit4mago:1>, s4bit4mago_illu,animal,anime style, hood, stuffed toy,
Réglages
Sampler
DPM++ 2M
Étapes
28
Guidance
6
Seed
135177849214208
Taille
3000x2472
Prompt
gigi murin \(1st costume\), shocked, solo, embedding:positive\illusp0s
Prompt négatif
embedding:Negative\IllusN3g, v shaped eyebrows, blush, looking at viewer
Réglages
Sampler
Euler a
Étapes
25
Guidance
5
Seed
4075875229
Taille
1536x1536
Prompt
1girl, <lora:Joy_-_Mobile_Legends_Bang_Bang:0.8> yellow hair, short hair, animal ears, aqua eyes, green jacket, scarf, hair ornament, gloves, <lora:rifle_shoulder_carry_ill_v1.0:1>, sh0uld3r_c4rry, weapon on shoulder, one arm up, hand on weapon, <lora:remington_870_shotgun:0.8> shotgun, remington 870, sitting, ruins, wasteland, dust, particles
Réglages
Sampler
Euler a
Étapes
20
Guidance
5
Seed
1456171850
Taille
1024x1536
Prompt
<lora:Apollousa, Bow of the Goddess illuXL v1.1:0.8> apollousa bow of the goddess, 1girl, green dress, looking down, black elbow gloves, forehead jewel circlet, black thighhighs, holding white glwoing bow \(weapon\), white hair, black boots, navel, (arrow \(projectile\)), sideboob, transparent wings, in air, legs up, shooting down, wide angle, looking down, sea, floating particles, nature, moon, knight, mountains, fog, shining mist, glowing water, mysterious,
Réglages
Sampler
Euler a
Étapes
25
Guidance
5
Seed
2857300433
Taille
896x1152
Prompt
1girl, blond hair, black military suit, armored vest, vv4zooo, sniper rifle, silencer, hand on rifle, holding rifle, <lora:wa2000_ill_v2.2:1> outdoor, <lora:bpre_ill_v3:0.5> bpre, night, front view, angled view, <lora:Smooth Booster:0.4>
Réglages
Sampler
Euler
Étapes
20
Guidance
5
Seed
698395561
Taille
840x1248
Prompt
a really cool giant robot in the style of tengen toppa gurren lagann, best quality,
Prompt négatif
worst quality, bad quality, bad anatomy, jpeg artifacts, signature, watermark, patreon username, text, speech bubble, censored, sketch, error, bad hands, extra digits, simple background,
Réglages
Sampler
Euler
Étapes
20
Guidance
5
Seed
2723353453
Taille
840x1248
Prompt
a really cool giant robot in the style of tengen toppa gurren lagann, battle scene!!, best quality,
Prompt négatif
worst quality, bad quality, bad anatomy, jpeg artifacts, signature, watermark, patreon username, text, speech bubble, censored, sketch, error, bad hands, extra digits, simple background,
Réglages
Sampler
Euler
Étapes
20
Guidance
5
Seed
340250660
Taille
840x1248
Prompt
houshou marine, party dress, best quality, absurdres,
Prompt négatif
worst quality, bad quality, bad anatomy, jpeg artifacts, signature, watermark, patreon username, text, speech bubble, censored, sketch, error, bad hands, extra digits, simple background,
Modèles d'IA pour générer image, vidéo et texte
simpleill vtower xl est un modèle de base pour la famille Stable Diffusion XL 1.0, 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 XL 1.0, 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