Model
Trends
.ai
Model
Trends
.ai
les meilleurs modèles d'IA open source
Exécuter en local
everclearPNYByZovya_v4.safetensors
6.46 GB · SafeTensor · fp16 · pruned
Les téléchargements sont servis par Civitai. Certains créateurs demandent d'abord une connexion à Civitai.
AD
<everclear4-xl>
À propos de ce modèle
STABLE DIFFUSION XL 1.0 · Modèles de base
Créé par
Zovya
sur Civitai
Model by Zovya. Guidance should range from 7 to 10, higher than other models. You can experiment with different samplers. I prefer DPM2M /karras .Prompting for quality should use the score system like other PonyXL models. (score_9, score_8_up, score_7_up) in the positive prompt and (score_3_up, score_4_up, score_5_up) in the negative prompt. Otherwise your images will be very plain.
Notes du créateur
Does everything a PonyXL model can, but "nearly" photorealistic! V4 update, improved faces and lighting trained in. Workflow I use to create the preview images What it does: If you're familiar with Pony models, they are very specific in their prompting and subject focus. I made this model to work the same way, but get closer to photorealistic. It uses the same prompting and LoRAs that other PonyXL models use. What it doesn't do: It's not a general model. Like other PonyXL models, it's more designed to work with booru tags and mostly does images with people in them. If you want to make general images, use a standard SDXL model. What's coming: PonyXL is trained on images with "exaggerated" anatomy. So I've purposely kept it from getting too photorealistic for the moment due to uncanny valley issues. As I train it more, I'll bring it closer to photoreal. In the meantime, use prompts such as (realistic photograph, depth of field, bokeh, etc) to help get the photo look. How to use: I recommend using the standard SDXL VAE. CFG should range from 7 to 10, higher than other models. You can experiment with different samplers. I prefer DPM++ 2S a Karras for consistency and DPM++ 3M SDE Exponential to get wild. Prompting for quality should use the score system like other PonyXL models. (score_9, score_8_up, score_7_up) in the positive prompt and (score_3_up, score_4_up, score_5_up) in the negative prompt. Otherwise your images will be very plain. Alternately, you can use the that I created for much easier use.
12,130 téléchargements · 1,216 j'aime sur Civitai
SHA256
6673BD3A26010D0AB3FC2E765803F6B04E426F5162D2FA7BAF93293623D8D37B
ID de modèle ModelTrends.ai
#10943
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 Karras
Étapes
20
Guidance
9
Seed
722727892714678
Taille
832x1216
Prompt
(zPDXL3) beautiful girl with vivid (rainbow dye, colored hair:1.3), smile, long hair, very long hair, (wavy hair:0.9), bangs, at a carnival at night, wearing a white sweater, realistic photograph, professional photographer, depth of field, bokeh
Prompt négatif
child, teeth, brunette, brown, teeth, makeup, (nude, rating_explicit, nsfw, source_anime, source_cartoon, blurry)
Réglages
Sampler
DPM++ 2M Karras
Étapes
20
Guidance
9
Seed
1056272890615462
Taille
832x1216
Prompt
(zPDXL3) dappled sunlight, realistic photograph of little red riding hood in a dark forest sitting on the ground, wearing a red hooded cloak, red dress and boots, leather pants
Prompt négatif
child, from behind
Réglages
Sampler
Euler a
Étapes
10
Guidance
6
Seed
1331282704
Taille
832x1216
Clip skip
2
Prompt
boneswm (MANDALA boneswm) (mandala geometric) (BONES radiating from a central mandala) (fractal BONE designs mandala) (Geometric BONE patterns mandala)
Prompt négatif
3d, photo, realistic, anime, source_furry, ((bad quality, worst quality)), blurry, black and white photo, nude
Réglages
Sampler
DPM++ 2M Karras
Étapes
20
Guidance
9
Seed
612476313497802
Taille
832x1216
Prompt
(zPDXL3) photo, ginger woman with red hair, long hair, freckles, in luxurious nightclub, sitting at the bar holding a beer, wearing a sweater and jeans, bokeh
Prompt négatif
teeth, brunette, brown, teeth, muscular, (nude, large breasts, rating_explicit, nsfw, source_anime, source_cartoon, blurry)
Réglages
Sampler
Euler a
Étapes
30
Guidance
10
Seed
1886026628
Taille
944x1216
Prompt
score_7, score_8, score_9, break, 1girl, solo, beautiful, sexy, alluring , ((freckles)) , body freckles, glossy skin, dramatic lighting, dark eyeshadow, false eyelashes, makeup , lip gloss, winged eyeliner, backlit , sultry, seductive, soft light , photo realistic , detailed skin, sharp focus, , volumetric lighting, ultrasharp, sharp eyes, sharp facial features, looking lustfully at viewer, backlit, <lora:Expressive_H:0.5> ,expressiveh, <lora:g0th1cPXL:0.5> ,g0th1cpxl, , ,wide angle , Dutch angle, golden hour, large tree, cherry blossom tree, heart shaped leaves, picturesque , detailed landscape, legs hanging down ,midriff, navel, high neck high low dress, no cleavage, , legs, hair blowing in the light breeze, brown hair, brown eyes, large breasts, 20 year old, gothic, alone, lonely, loneliness, sad, sadness, darkness, hopeless romantic, perfect shadows, imagination, dark fantasy, passion, <lora:Crystal_Heart_Style:.7>, heart shaped crystals falling from the tree, flower hearts, leaf hearts, crstheart, crystal, flower, light particles, light rays,
Prompt négatif
score_6, score_5, score_4, ugly face, low res, blurry face, black and white, muscular female , aidxlv05_neg, negative_v2, negativeXL_D, censored, greyscale, sketch, bad hands, ugly, bad feet , watermark , tan lines , large belly , large stomach , watermark, text, extra arms, extra legs, shoes, heels, multi arms, multi legs, bad hand anatomy, bad finger anatomy, unclear architectural outline, non-linear background,
Réglages
Sampler
Euler a
Étapes
40
Guidance
3.5
Seed
236735465
Taille
832x1216
Clip skip
2
Prompt
a skeleton clock sitting in the middle of a street, 3d rendered steampunk, muscular eldritch clockwork, cyberpunk skeleton, clockpunk, robot skeleton, steampunk automaton, high quality steampunk art, clockwork steampunk, skelleton, clockwork mechanical, titanium skeleton, tall skeletal figure, clockwork automaton, clockwork horror, mechanical clock, inter dimensional clockwork, 4 k human detailed!!! (starry night) starry_morph
Réglages
Sampler
DPM++ 2M
Étapes
20
Guidance
7
Seed
1544044352
Taille
832x1216
Prompt
zPDXL3 zPDXLpg zPDXLrl beautiful girl with vivid (rainbow dye, colored hair:1.3), smile, long hair, very long hair, (wavy hair:0.9), bangs, at a carnival at night, wearing a white sweater, realistic photograph, professional photographer, depth of field, bokeh
Prompt négatif
zPDXLpg-neg zPDXLrl-neg teeth, brunette, brown, teeth, muscular, (nude, rating_explicit, nsfw, source_anime, source_cartoon, blurry)
Réglages
Sampler
DPM++ 2M Karras
Étapes
20
Guidance
9
Seed
769582106865883
Taille
832x1216
Prompt
(zPDXL3) 2girls, beautiful, colorful hair, cyberpunk nightclub, sofa, chairs, bodysuit, robes, coffee table, low light, dark, (hugging:0.5), lounge, night, cityscape in the background
Prompt négatif
from behind, teeth, cybernetics, (nude, child, rating_explicit, large breasts, cleavage, nsfw, source_anime, source_cartoon, covered nipples, blurry)
Modèles d'IA pour générer image, vidéo et texte
everclear4 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