Model
Trends
.ai
Model
Trends
.ai
les meilleurs modèles d'IA open source
Exécuter en local
AissistXLv2-neg.pt
1 MB · Other
AissistXLv2.safetensors
1 MB · SafeTensor
Télécharger
Les téléchargements sont servis par Civitai. Certains créateurs demandent d'abord une connexion à Civitai.
À propos de ce modèle
STABLE DIFFUSION XL 1.0 · Embeddings
Créé par
kayfahaarukku
sur Civitai
__html__AissistXL is a negative embedding fine-tuned to be working on Animagine XL v3 and its derivatives. It trained on the standard negative prompt for Animagine XL v3 plus some extra parameters to make sure you always generate the best possible images with Animagine-based models. You can also try to use this negative embedding for other SDXL-based models, but output quality is not guaranteed.You don't necessarily need to use Animagine default negatives if you're using this negative embedding.FAQQ: Will it work on Pony-based models?A: Standalone? No. Combined with Pony-specific negative prompts? Maybe.Q: If CagliostroLab releases a new Animagine XL version, will this negative embedding still work?A: Yes.
Notes du créateur
AissistXL is a negative embedding fine-tuned to be working on and its derivatives. It trained on the standard negative prompt for Animagine XL v3 plus some extra parameters to make sure you always generate the best possible images with Animagine-based models. You can also try to use this negative embedding for other SDXL-based models, but output quality is not guaranteed. You don't necessarily need to use Animagine default negatives if you're using this negative embedding. FAQ Q: It's showing errors on AUTOMATIC1111, saying it's unsafe, and won't load the Embedding. A: It's safe, it showing that error because the embedding still using .pt files. You can either put --disable-safe-unpickle on your AUTOMATIC1111 arguments, or download the .safetensors one I provided as "Embedding" (Negative is the .pt one). Q: Will it work on Pony-based models? A: Standalone? No. Combined with Pony-specific negative prompts? Maybe. Q: If CagliostroLab releases a new Animagine XL version, will this negative embedding still work? A: Yes.
Mots déclencheurs
AissistXLv2
11,306 téléchargements · 543 j'aime sur Civitai
SHA256
0CB60611A3E1D0E4E1C8B02647169AAAA1F0306ADA8C0216EC4EFAF1C05C1AAE
ID de modèle ModelTrends.ai
#9291
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
DPM++ 2M SDE Heun
Étapes
40
Guidance
4
Seed
6047143
Taille
1216x832
Clip skip
2
Prompt
masterpiece, high score, great score, absurdres, 1girl, Samus Aran receiving a chocolate box, blushing, valentine gift, baby Metroid, hearts, standing, from side, abstract background, volumetric lighting
Prompt négatif
lowres, bad anatomy, bad hands, text, error, missing finger, extra digits, fewer digits, cropped, worst quality, low quality, low score, bad score, average score, signature, watermark, username, blurry, AissistXLv2-neg
Réglages
Sampler
Euler a
Étapes
28
Guidance
5
Taille
1280x1856
Clip skip
2
Poids utilisé
1
Prompt
masterpiece, best quality, perfect quality, very awa, absurdres, newest, very aesthetic, female furry, kindred (lol), lamb, white fur, long ears, mask, glowing eyes, blue eyes, fluffy, markings, voluptuous body, upper body, thighs, close-up, detailed background, depth of field, under shade, under tree, reclining, falling leaf, blue and green color palette, limited palette, poster art
Prompt négatif
unaestheticXL_cbp62, AissistXLv2, negativeXL_D
Réglages
Sampler
DPM++ 2M Karras
Étapes
35
Guidance
7
Seed
2462429700
Taille
768x1280
Clip skip
2
Prompt
<lora:add-detail-xl:0.5>, , <lora:helldivers:0.8> helldivers , woman, facing away, skimpy armor, large ass, human handprint on ass, facing a monster, volumetric lighting, depth of field, key visual,, super detailed picture, high resolution, 10k, 8k, finely detailed, quality,, Cinematic portrait photography, capture subject in a way that resembles a still frame from a movie, cinematic lighting, story, narrative quality, drawing viewers into the scene and evoking a sense of cinematic immersion, capturing emotion, professional, engaging, compelling composition, wildlife photography, capturing nature's beauty, breathtaking landscapes, immersive experience, storytelling through imagery, showcasing wildlife behavior, sharp details, evocative composition, unique perspective
Prompt négatif
AissistXLv2, ac_neg1, aidxlv05_neg, ImgFixerPre0.3, negativeXL_D, unaestheticXL_Alb2, bad anatomy, comics, cropped, cross-eyed, worst quality, low quality, painting, 3D render, drawing, crayon, sketch, graphite, impressionist, cartoon, anime, noisy, blurry, soft, deformed, ugly, lowres, low details, JPEG artifacts, airbrushed, semi-realistic, CGI, render, Blender, digital art, manga, amateur, mutilated, distorted, bad anatomy, comics, cropped, cross-eyed, worst quality, low quality, painting, 3D render, drawing, crayon, sketch, graphite, impressionist, cartoon, anime, noisy, blurry, soft, deformed, ugly, lowres, low details, JPEG artifacts, airbrushed, semi-realistic, CGI, render, Blender, digital art, manga, amateur, mutilated, distorted
Réglages
Sampler
Euler a
Étapes
28
Guidance
7
Seed
706602653
Taille
832x1216
Clip skip
2
Prompt
1girl, bronya zaychik, honkai impact 3rd, honkai \(series\), medium hair, wavy hair, twintails, silver hair, grey eyes, small breasts, dress, frills, white background, simple background, sketch, lam \(ramdayo\), masterpiece, best quality, very aesthetic, absurdres,
Prompt négatif
AissistXLv2,
Réglages
Sampler
Euler a
Étapes
28
Guidance
7
Seed
4187154237
Taille
832x1216
Prompt
1girl, original, hiding, hiding in grass, kneeling, (solo:1.1), athletic, medium breasts, intricate light pink hair, very long hair, twintails, high twintails, long twintails, uneven twintails, purple eyes, alluring smile, sundress, bare legs, cleavage, detailed ultra photorealistic marsh, tree, (very tall grass:1.2), dappled sunlight, golden hour lighting, sunrise, great lighting, cinematic angle, anime artwork, anime style, key visual, vibrant, studio anime, anime coloring, highly detailed, newest, masterpiece, best quality, <lora:great_lighting:3> <lora:Difference_AnimeFace:0.85>
Prompt négatif
AissistXLv2-neg, oldest, early, artistic error, scan, [abstract], photo, black and white, realism, disfigured, low contrast, lipgloss, curly hair, (parted bangs:1.2), sketch, (nose:0.8), colored inner hair, child, key, forehead, bangle, sweatband, (nose:0.85), heterochromia, backlighting, shaded face
Réglages
Sampler
DPM++ 2M Karras
Étapes
35
Guidance
7
Seed
2462429700
Taille
768x1280
Clip skip
2
Prompt
<lora:add-detail-xl:0.5>, , <lora:helldivers:0.8> helldivers , woman, facing away, skimpy armor, large ass, human handprint on ass, facing a monster, volumetric lighting, depth of field, key visual,, super detailed picture, high resolution, 10k, 8k, finely detailed, quality,, Cinematic portrait photography, capture subject in a way that resembles a still frame from a movie, cinematic lighting, story, narrative quality, drawing viewers into the scene and evoking a sense of cinematic immersion, capturing emotion, professional, engaging, compelling composition, wildlife photography, capturing nature's beauty, breathtaking landscapes, immersive experience, storytelling through imagery, showcasing wildlife behavior, sharp details, evocative composition, unique perspective
Prompt négatif
AissistXLv2, ac_neg1, aidxlv05_neg, ImgFixerPre0.3, negativeXL_D, unaestheticXL_Alb2, bad anatomy, comics, cropped, cross-eyed, worst quality, low quality, painting, 3D render, drawing, crayon, sketch, graphite, impressionist, cartoon, anime, noisy, blurry, soft, deformed, ugly, lowres, low details, JPEG artifacts, airbrushed, semi-realistic, CGI, render, Blender, digital art, manga, amateur, mutilated, distorted, bad anatomy, comics, cropped, cross-eyed, worst quality, low quality, painting, 3D render, drawing, crayon, sketch, graphite, impressionist, cartoon, anime, noisy, blurry, soft, deformed, ugly, lowres, low details, JPEG artifacts, airbrushed, semi-realistic, CGI, render, Blender, digital art, manga, amateur, mutilated, distorted
Réglages
Sampler
Euler a
Étapes
28
Guidance
7
Seed
111260541
Taille
896x1152
Clip skip
2
Prompt
1girl, gotoh hitori, bocchi the rock!, long hair, blue eyes, pink hair, cube hair ornament, open mouth, wavy mouth, large breasts, black t-shirt, grey skirt, arms behind back, forest, river, looking at viewer, outdoors, masterpiece, best quality, very aesthetic, absurdres,
Prompt négatif
AissistXLv2,
Réglages
Sampler
DPM++ 2M Karras
Étapes
35
Guidance
7
Seed
4042725827
Taille
768x1280
Clip skip
2
Prompt
there is a dog with a fish and a sword on a white background, samurai fox, fox warrior, armored fox, anthropomorphic fox ninja, samurai deity with koi armor, by Kanō Tan'yū, highly detailed and colored, in the art style of ukiyo - e, inspired by Utagawa Kuniyoshi, <lora:add-detail-xl:0.35>, super detailed picture, high resolution, 10k, 8k, finely detailed, quality,, Japanese traditional art style, delicate lines, subtle colors, intricate details, dynamic compositions, cultural heritage, adds elegance and sophistication, Chinese ink brush art style, graceful brushwork, elegant compositions, traditional motifs, professional-grade execution, captures the essence of Chinese culture and aesthetics
Prompt négatif
AissistXLv2, ac_neg1, aidxlv05_neg, ImgFixerPre0.3, negativeXL_D, unaestheticXL_Alb2, signature, watermark, photo, photorealistic, realism, ugly, off-center, deformed, 35mm film, dslr, cropped, frame, worst quality, low quality, lowres, JPEG artifacts, Chinese writing, signature, watermark, photo, photorealistic, realism, ugly, off-center, deformed, 35mm film, dslr, cropped, frame, worst quality, low quality, lowres, JPEG artifacts
Badges for creators
Made this model? Put its standing on your Civitai page, your Hugging Face card, your README or your site. Each badge is a small picture that shows the standing on the day you copy it and never changes afterwards, however the rankings move later. The date is part of the badge.
aissist on ModelTrends.ai: #24 of 77 Stable Diffusion XL 1.0 embeddings
Modèles d'IA pour générer image, vidéo et texte
aissist xl est un embedding 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