Model
Trends
.ai
Model
Trends
.ai
les meilleurs modèles d'IA open source
Exécuter en local
knkKirimagineAnimagine_v20.safetensors
6.46 GB · SafeTensor · fp16 · pruned
Les téléchargements sont servis par Civitai. Certains créateurs demandent d'abord une connexion à Civitai.
AD
<knk-kirimagine-xl>
À propos de ce modèle
STABLE DIFFUSION XL 1.0 · Modèles de base
Créé par
Konoko
sur Civitai
by Konoko - KNK Kirimagine (Animagine v4)
Notes du créateur
None of the images in the previews were up-scaled, detailed, or treated beyond adjusting the sampling steps. This model was created with the goal of providing better stability when using , while giving it a cute, soft style based on a dataset extracted from my model . Read the version notes below Features - No extensive negative tags required: Works relatively well with just a few quality control tags like "low score, worst quality". Adding more may improve results. - Improved limb generation: Produces better anatomy right out of the box. - LoRA compatibility: It should work well with Illustrious LoRAs. - Faithful native style representation: Thanks to the original creators, the styles were somewhat "overcooked," which helps maintain them even after fine-tuning or merges. - User-friendly: Simple and intuitive to use, especially compared to the base model. - Good language compatibility: The SDXL base was re-merged into the model, slightly improving natural language comprehension. How to Use Since this model is purely based on , you should follow their guidelines. However, here are some additional recommendations: - Follow the prompt structure: This makes a big difference when generating characters. You can shorten the "series" weight to make it easier to change the character's style. Example: "1girl/1boy/1other, character name, from which series, everything else in any order." - Most of the time, you’ll need "low score" in the negative prompts, but removing it can help create fun generations and simpler styles. Why Use This Model? You might be wondering, "Why would I use another model if I already have PonyV6 and Illustrious?" While this model isn't as stable as Illustrious or as rich in resources as PonyV6 (LoRAs and custom models), it does offer several advantages: - Updated character dataset: Unlike NoobAI (which is more of a "patch" over Illustrious), this model is updated from its core. - Better understanding of certain concepts (…most of them are NSFW, but compared with illustrious, it lacks on multi characters compositions). - Compatibility with Illustrious LoRAs. - Produces more vibrant and dynamic images than the base Illustrious/NoobAI models, with stronger contrast—without needing to rely on v-pred models. - Smells like apple. 🍏 Version 2 This was a little nightmare, this model is just broken internally. I had to almost re-place the Clip using a lot of LoRas and the base SDXL. The base style was made using the data set of my model and my lora . In general performs much better than the version 1, Ani4 base, zero or opt. I'm sure of that, but isn't good as Illustrious base models are for complex compositions and multi-characters. But I feel Ani4 better in some aspects like colors, dataset, and single character compositions. Version 1 This model was fine-tuned using a relatively small dataset to stabilize the default style and set high-quality images as the default aesthetic. While it still has issues with hands, these are significantly reduced compared to the original model. My goal is to continue refining this model to minimize these issues without sacrificing its flexibility. License This model cannot be used for commercial purposes, modifications, or distribution without explicit consent. In other aspects, it follows the .
508 téléchargements · 35 j'aime sur Civitai
SHA256
B993AB09412EAE84E26C12604B5B648D12DA89B5EF79D7218B6EC2F3289DE7A2
ID de modèle ModelTrends.ai
#17947
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
32
Guidance
5
Seed
3551553698
Taille
1200x1512
Clip skip
2
Prompt
1girl, rabbit girl, fluffy hair, open mouth, smile, dutch angle, sunlight, outstretched arm, fisheye, buck teeth, frills, long ribbon, sunlight, arched back, from side, clock tower, shiny_hair, from above, v, standing on one leg, outdoors, cityscape, medium breasts, light particles, magical girl, on rooftop, selfie, floating hair, long locks, neck bell, dark blue hair, very long hair, sunset, hair between eyes, multicolored eyes, body freckles, ears down, ears back, long eyelashes,sleeves past elbows, high score, masterpiece,
Prompt négatif
worst quality, simple background, kaname madoka,
Réglages
Sampler
Euler a
Étapes
24
Guidance
5
Seed
2612533289
Taille
896x1152
Clip skip
2
Prompt
1girl, ghost miku \(project voltage\), playing chess, confused, open mouth, <lora:kotoba-kun_style_illustrious01_v1_20:.9>
Prompt négatif
worst quality
Réglages
Sampler
Euler a
Étapes
24
Guidance
5
Seed
36972431
Taille
1200x1512
Clip skip
2
Prompt
1girl, gawr gura, chibi, flat colors , solid oval eyes, open mouth ,smug, holding a sign with text "wtf", digital media, meme attire, shark tail, bad score
Réglages
Sampler
Euler a
Étapes
22
Guidance
5
Seed
3594585908
Taille
896x1152
Clip skip
2
Prompt
1girl, bottle miku, liquid hair, fish , wading, looking up, rain, dutch angle, sanctuary, masterpiece, high score
Prompt négatif
worst quality, simple background,
Réglages
Sampler
DPM++ SDE
Étapes
40
Guidance
5
Seed
3149360972
Taille
896x1152
Clip skip
2
Prompt
1girl, (lumine \(genshin impact\):0.8) , genshin impact,realistic, high contrast, lips, dynamic pose, looking at away,white dress, high score, hair hair ornament, reflective_eyes, looking at viewer, dark background, (black background:0.8),reflective water, reflection, depth of field, blurry foreground, feathers, candlelight, depth of field, from above, chiaroscuro, wading, glowing water, lens flare, cathedral, from above,full body,dutch angle, water waves, fisheye, twilight, thighhighs, from side
Prompt négatif
worst quality, simple background,
Réglages
Sampler
Euler a
Étapes
24
Guidance
5
Seed
3707257032
Taille
896x1152
Clip skip
2
Prompt
1girl, (raphtalia:0.8), hatsune miku \(cosplay\), pout, headpat, raccoon girl, twintails, crossed legs, thighhighs, from above,
Prompt négatif
worst quality
Réglages
Sampler
Euler a
Étapes
22
Guidance
5
Seed
1565939757
Taille
896x1152
Clip skip
2
Prompt
1girl, bob cut, dark blue hair, hairband, red band, white dress, frilled dress, mary janes, round eyewear, blue eyes, leaning on railing, cityscape, sunlight, pink lips, long sleeves, tiptoes, (Morikura En:1.05), Rella,(nanaken nana:0.9524),u u zan, banishment, stu dts,(miv4t:0.9524),(wlop:0.907) (suzumi \(ccroquette\):1.1025),rei \(sanbonzakura\),torino aqua,close-up, squatting, realistic, dutch angle,
Prompt négatif
worst quality, simple background,
Réglages
Sampler
Euler a
Étapes
28
Guidance
5
Seed
4004118527
Taille
896x1152
Clip skip
2
Prompt
1girl, anya \(spy x family\), khyle.,black coat, organization xiii, big heartless \(kingdom hearts\), (multiple enemies:1.3),keyblade, battle attire, frown, serious, shorts, wind lift, frown, serious, half-closed eyes, reflective floor, holding keyblade, dutch angle, hood up, looking at enemy, stained glass, masterpiece, high score, legs apart, twilight, blue theme, scenery,
Modèles d'IA pour générer image, vidéo et texte
knk kirimagine 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