Model
Trends
.ai
Model
Trends
.ai
les meilleurs modèles d'IA open source
NSFW
Modèle NSFW. Ses images sont masquées tant que NSFW est désactivé ; activez NSFW pour les voir.
Exécuter en local
longneck.safetensors
36 MB · SafeTensor
Les téléchargements sont servis par Civitai. Certains créateurs demandent d'abord une connexion à Civitai.
À propos de ce modèle
STABLE DIFFUSION 1.5 · LoRA
Créé par
_NSFW_
sur Civitai
__html__Makes necks a bit longerer, or very very longerer, you decide! Supports the following prompts in order of length: extended neck, long neck, stretched neck, looped neck, rokurokubi. Also has a little bit of giraffe skin texture trigger baked in (ymmv). It can do realistic and some anime/drawings.If you want looped neck / rokurokubi, be prepared to mess with weights (I find 1.2 for the trigger words works best) and do quite a bit of cherry picking (I sometimes had to generate 20 base images before finding one worth upscaling). When the neck starts connecting better you'll know you're getting the tuning right!Best results were with transformix v1 at a weight of 1. Generally I find that turning the lyco down for img2img (.8 or so) gives better looking necks. Sometimes turning the trigger word weight can allow you to turn the lyco weight down for img2img.
Notes du créateur
Makes necks a bit longerer, or very very longerer, you decide! Supports the following prompts in order of length: extended neck, long neck, stretched neck, looped neck, rokurokubi. Also has a little bit of giraffe skin texture trigger baked in (ymmv). It can do realistic and some anime/drawings. If you want looped neck / rokurokubi, be prepared to mess with weights (I find 1.2 for the trigger words works best) and do quite a bit of cherry picking (I sometimes had to generate 20 base images before finding one worth upscaling). When the neck starts connecting better you'll know you're getting the tuning right! Best results were with transformix v1 at a weight of 1. Generally I find that turning the lyco down for img2img (.8 or so) gives better looking necks. Sometimes turning the trigger word weight can allow you to turn the lyco weight down for img2img.
Mots déclencheurs
longneck
846 téléchargements · 116 j'aime sur Civitai
SHA256
EACA3B4814D8B54F9C441615FA96C093FA80A759D37AA72924C938FC202B9B67
ID de modèle ModelTrends.ai
#3163
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
26
Guidance
10
Seed
1753917578
Taille
512x768
Clip skip
2
Poids utilisé
1
Prompt
cactus plant, on a table, next to cute massive huge crazy eyes (long neck) kittens with wearing hats, 4k, high detail, high quality, realistic, cats going nuts! Cats pog, fangs, Crazy smile, glowing eyes,
Prompt négatif
lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark,username, blurry, nsfw, humans, low quality, bad resolution,
Réglages
Sampler
DPM++ 2M Karras
Étapes
20
Guidance
7
Seed
3358074924
Taille
1024x1820
Clip skip
2
Prompt
(ultra realistic, highly detailed:1.4), best quality, masterpiece, spiderman <lora:longneck:0.5> ((longneck):1)
Prompt négatif
easynegative, bad-hands-5, (low quality, worst quality:1.3), child, boring_e621, naked, nude
Réglages
Sampler
Euler a
Étapes
24
Guidance
6
Seed
3383140093
Taille
1360x1024
Prompt
1girl, upper body, skinny, starving woman, long neck, no face, <lora:longneck:0.8>, <lora:无面:2.5>, dark theme, <lora:lowra_v10:0.7>, vhs, vhs footage of <lora:badVHS_v101:1>, outside, exterior, outdoors, background, exterior, scenery, perfect composition, night, spotlight, film grain
Prompt négatif
(face, eyes, mouth, nose:1.2), (Geometric pattern:0.8), (duplicate:1), (unclear background:1.1)
Réglages
Sampler
Euler a
Étapes
24
Guidance
6
Seed
3383140096
Taille
1360x1024
Prompt
1girl, upper body, skinny, starving woman, long neck, no face, <lora:longneck:0.8>, <lora:无面:2.5>, dark theme, <lora:lowra_v10:0.7>, vhs, vhs footage of <lora:badVHS_v101:1>, outside, exterior, outdoors, background, exterior, scenery, perfect composition, night, spotlight, film grain
Prompt négatif
(face, eyes, mouth, nose:1.2), (Geometric pattern:0.8), (duplicate:1), (unclear background:1.1)
Réglages
Sampler
Euler a
Étapes
30
Guidance
8
Seed
55509980
Taille
768x768
Clip skip
2
Prompt
<lora:allVtubersLora_hll31:1> (selen tatsuki:1.2), virtual youtuber, <lora:longneck:1.3> longneck, 1girl, vibrant beautiful painting of portrait of a diesel punk Rei Ayanami on the art deco streets of the big city, artstation, award-winning realistic sci-fi concept art by Jim Burns and Greg Rutkowski, Picasso, Beksinski, masterpiece, complimentary colors, James Gilleard, Bruegel, Alphonse Mucha, and Yoshitaka Amano
Prompt négatif
(easynegative:0.8),
Réglages
Sampler
Euler a
Étapes
30
Guidance
10
Seed
1282307491
Taille
768x768
Clip skip
2
Prompt
<lora:allVtubersLora_hll31:1> (selen tatsuki:1.2),virtual youtuber,<lora:longneck:1.3>,(longneck:1.3),1girl,the wandering earth, intricate artwork by tooth wu and wlop and beeple. octane render, trending on artstation, greg rutkowski very coherent symmetrical artwork. cinematic, hyper realism, high detail, octane render,
Prompt négatif
(easynegative:0.8),
Réglages
Sampler
DPM++ 2M Karras
Étapes
25
Guidance
6
Seed
100
Taille
512x768
Clip skip
2
Prompt
1girl, longneck, smiling, detailed clothes, look at viewer, best quality, masterpiece, hires, depth of field, detailed background, diffused natural sunlight, diffused natural skin glow, <lora:longneck:1>
Prompt négatif
EasyNegative, worst quality, low quality, zombie, logo, text, watermark, username, monochrome
Réglages
Sampler
Euler a
Étapes
24
Guidance
6
Seed
2982729799
Taille
1024x1360
Prompt
1girl, upper body, skinny, starving woman, long neck, no face, <lora:longneck:0.8>, <lora:无面:2.5>, dark theme, <lora:lowra_v10:0.7>, vhs, vhs footage of <lora:badVHS_v101:1>, film grain
Prompt négatif
(face, eyes, mouth, nose:1.2)
Modèles d'IA pour générer image, vidéo et texte
long necks21 est un LoRA 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