Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
ynsReal_v3.safetensors
6.46 GB · SafeTensor · fp16 · pruned
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<ynsreal3-xl>
About This Model
STABLE DIFFUSION XL 1.0 · Base Models
Created by
yakinamashake
on Civitai
by yakinamashake - YNS-Real
Creator notes
※全てのモデルにはLoraがマージされています。 V3は、illustrious-XLのキャラクター再現を復活させつつ、リアルな質感を維持できるように工夫しました。また、danbooru語の追従性も大幅に改善していると思います。 ※一部の画像のメタデータ内、生成に使ったモデル名が別名になっているかもしれませんが、V3とまったく同じモデルです。 V2testは、アニメキャラクターの再現度はほぼ無く、さらにdanbooru語の追従性は劣りますが、V3よりもリアルさはやや高いと思います。 V1...?　好みで使ってください。 おそらく（少なくともしばらくは）このYNSrealシリーズの更新はありません。 チップやコメントなどの反応ありがとうございます。 画像の投稿など助かります。 下記は私が生成する際の設定です。参考にしてください。 - width×height 1152×1536 - ポジティブプロンプト（下記を含める） photograph, realistic, cosplay, beautiful detailed, high contrast, hazy light, portrait, masterpiece, very awa, highres, best quality, sharp focus, - ネガティブプロンプト（下記を含める） worst quality, low quality, normal quality, lowres, low details, blurry, sketch, oil paint, anime, cartoon, anime coloring, 2D, illustration, american, european, african, bodyhair, male, boy, - Sampling method DPM++ SDE - Schedule type Karras - Sampling steps 28 - Hires. fix　Upscaler 4xFaceUpDAT　 - Hires steps 15 - ADetailer face_yolov8s.pt photograph, realistic, cosplay, beautiful detailed, high contrast, hazy light, portrait, masterpiece, very awa, highres, best quality, sharp focus, 1girl, (キャラクター名), (コピーライト名), (必要であれば表情タグ）, face focus, close-up, tips dark skinやdark-skinned femaleを指定すると、元モデルが学習している黒人の特徴が出る傾向があります。アジア人の褐色を求める場合は、dark skinやdark-skinned femaleを省き、代わりにsun-kissed skinを指定すると安定する場合があります。 プレゼント OpenAIのChatGPTのGPTsを使ったキャラクターとその外見特徴を出力するGPTsを作りましたので共有します。 ただし私の判断で共有を止めたり、更新による改悪があるかもしれません。 また、2025年の4月ごろにdanbooruのAPIを叩いた時のpost数（投稿数）の上位５０００人分の情報になります。（4月時点でポストカウントが470以上のキャラクター） 取得方法により間違ったタグ情報を取得している可能性があります。wikiのurlも出すようにしているのでwikiで情報を確認して、より正確なタグを使ってください。 リンクを知っている人のみに公開しています。('ω')
5,540 downloads · 611 likes on Civitai
SHA256
BC0C6D1CE2805585F7599E25766E39114A33886220CB581E951671CB66BF88BE
ModelTrends.ai Model ID
#15968
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Size
1440x1920
Prompt
masterpiece, best quality, highres, absurdres, very awa, banana costume, full body, standing, spread arms, looking at viewer, white background, t-pose, hannah, ahoge, 5 fingers, black shoes, socks, furry, tiger girl, spread legs, empty eyes, jeans, high angle view, interesting angle, view from side, purple eyes <lora:Banana_CostumeILL:1> <lora:Hannah_Mahjong_Soul_Illustrious_v02:1>
Negative prompt
worst aesthetic, worst quality, lowres, scan artifacts, nudecleavage, explicit, questionable Steps: 30, Sampler: Euler a, Schedule type: Automatic, CFG scale: 3.5, Seed: 3782258825, Size: 960x1280, Model hash: f39adb475a, Model: ynsReal_v3, Denoising strength: 0.65, ENSD: 31337, Hires Module 1: Use same choices, Hires CFG Scale: 5, Hires upscale: 1.5, Hires upscaler: Latent (nearest-exact), Lora hashes: "Banana_CostumeILL: c24237666a10, Hannah_Mahjong_Soul_Illustrious_v02: efa4e28d6b83", Discard penultimate sigma: True, Eta: 0.67, Version: f2.0.1v1.10.1-previous-635-gf5330788
Settings
Sampler
DPM++ 2M SDE
Steps
35
Guidance
4.5
Seed
1936621081
Size
832x1216
Clip skip
2
Prompt
woman, statue, made of stone, (blindfold:1.2), blindfolded, marble, beautiful, cracks, face focus, close up,, masterpiece, best_quality, amazing_quality, very_aesthetic, 8k, high_quality, highres, absurdres, subject_focus,, blurry background, detailed shadows, atmospheric haze, ambient occlusion, shallow depth of field, film grain, vignette, motion blur, chromatic aberration,
Negative prompt
bad_quality, worst_quality, worst_detail, sketch, censor, poorly_detailed, jpeg_artifacts, (signature, watermark:1.4), print, logo, loli, minor, underage, child,
Settings
Sampler
DPM++ 2M SDE
Steps
35
Guidance
4.5
Seed
1936621080
Size
832x1216
Clip skip
2
Prompt
frog, cute, adorable, animal_focus, pond reflection, dramatic lighting,, masterpiece, best_quality, amazing_quality, very_aesthetic, 8k, high_quality, highres, absurdres, subject_focus,, blurry background, detailed shadows, atmospheric haze, ambient occlusion, shallow depth of field, film grain, vignette, motion blur, chromatic aberration,
Negative prompt
bad_quality, worst_quality, worst_detail, sketch, censor, poorly_detailed, jpeg_artifacts, (signature, watermark:1.4), print, logo, loli, minor, underage, child,
Settings
Sampler
DPM++ 2M SDE
Steps
28
Guidance
4.5
Seed
864568712
Size
960x1280
Prompt
suzuran \(arknights\), (aged up), black suit, white shirt, black tie, multiple tails, aiming staff at viewer, depth of field effect, (blurry foreground), holding staff, aiming at viewer, staff close up, ctaff tip close up, (((perspective))) view from side , looking at viewer , serious expression, standing, leaning back, cool pose, multiple tails, animal ears, many tails, yellow fox tails, large ears, onmyouji staff, holding staff, ruined city, neon glow, solo, nervous, fluffy fur, upper body view, black pants, glowing staff, F4st, interesting angle, cute, perspective, head turn, green eyes, glowing eyes, depth of field, blurry background, detailed eyes, detailed face, serious, jitome, slim, shortstack, yellow glow, blue glow, mist, chiaroscuro, casting magic, yellow magic glow, casting spell, spell, holding spell masterpiece, best quality, cinematic, sidelighting, outdoors, moonlight, formal clothes, cute,
Negative prompt
explicit, bad anatomy, low quality, questionable, cleavage, human ears, child, aged down, furry, snout, anthro
Settings
Sampler
DPM++ SDE
Steps
28
Guidance
4.5
Seed
2833811172
Size
1152x1536
Prompt
photograph, realistic, cosplay, beautiful detailed, high contrast, hazy light, portrait, masterpiece, very awa, highres, best quality, sharp focus, 1girl, amiya \(arknights\), arknights, blue eyes, brown hair, long hair, ponytail, rabbit ears, straight-on, ascot, hooded jacket , hood down, open jacket, wind, floating hair,
Negative prompt
worst quality, low quality, normal quality, lowres, low details, blurry, sketch, oil paint, anime, cartoon, anime coloring, 2D, illustration, american, european, african, bodyhair, male, boy,
AI Models for Image, Video & Text Generation
ynsreal3 xl is a base model for the Stable Diffusion XL 1.0 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion XL 1.0 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Browse all models