SDXL

illustriousWAI-ZimageStyle(梦歆·明绘)

illustriousWAI-ZimageStyle(梦歆·明绘) - AI Model cover image
Subido en
14 ene 2026, 22:24
Utiliza
1.3k
Reseñas
Sin reseñas
Permisos
  • Permitir la generación y el intercambio de imágenes
  • Permitir que los usuarios descarguen su modelo
  • Usos comerciales

LoRAs recomendadas

Descripción

https://civitai.com/models/2308503/illustriouswai-zimagestyle

“与其寻找一个Z的底模,不如创造的一个Z的底模。”推荐采样器 eular a,调度器beta,步数24~30,cfg5.5,分辨率大于等于1k(1024*1024)且为64的倍数建议进行高清修复我非常喜欢Zimage那明快清晰的画面与舒适的前后景配比,但其turbo模型的限制导致任何有关二次元的训练只不过是在不适合的基础上堆砌积木,随时会不稳坍塌。这时我想到了,为什么不依靠Z的重绘功能制作符合审美的素材,再将之迁移到二次元生态如此丰满的illustrious系模型上呢?所以就出现了这样一个模型,由于是临时起意,制作的素材并不多,但经过几番调整,出图效果已经达到我先前炼制Zimagelora的预期。后续我会继续研究各种组合,以提升更丰富的细节为目标继续优化这个模型。本模型是基于illustrious1.0训练的lycoris模型,融合wai-illustriousv16完成的,其中若有许多不稳定或是希望改进的地方,期待和我反馈![EN] I absolutely adore the bright, clear visuals and comfortable foreground-background balance of Zimage. However, its Turbo model limitations meant that any anime-related training felt like stacking blocks on an unstable foundation—prone to collapsing at any moment.Then it hit me: Why not use Zimage's img2img (inpainting/redrawing) capabilities to generate aesthetic training data, and then transfer that style onto the Illustrious ecosystem, which is so rich in anime resources?And so, this model was born. Since it was a spur-of-the-moment idea, the training dataset isn't huge yet. However, after several adjustments, the generation results have already met my original expectations for training a Zimage LoRA.Moving forward, I plan to research various combinations to optimize this model further, aiming for even richer details.Technical Specs:Base Model: Illustrious 1.0Type: LyCORISMerge: Fused with wai-illustriousv16Recommended Settings:Sampler: Euler aScheduler: BetaSteps: 24 ~ 30CFG Scale: 5.5Resolution: ≥ 1024x1024 (must be multiples of 64)If you encounter any instability or have suggestions for improvement, please let me know![JP] 私は Zimage の明るく鮮明な画面と、心地よい前後景のバランスが大好きです。しかし、そのTurboモデルという制限上、二次元(アニメ調)に関する学習は、不適切な土台の上に積み木を重ねるようなもので、いつ崩れてもおかしくない不安定さがありました。そこで思いついたのです。「Zimageのimg2img(再描画)機能を使って自分の美学に合う素材を作成し、それを二次元のエコシステムが充実している Illustrious 系モデルに移植すればいいのではないか?」と。そうして生まれたのがこのモデルです。思いつきで始めたため、学習素材はまだ多くありませんが、何度か調整を経た結果、以前ZimageでLoRAを作ろうとした時の期待値に達する出力が得られるようになりました。今後は、より豊かなディテールを目指して、様々な組み合わせを研究し、このモデルを最適化していく予定です。モデル仕様:ベースモデル: Illustrious 1.0タイプ: LyCORISマージ: wai-illustriousv16 を融合して完成させました。推奨設定:サンプラー (Sampler): Euler aスケジューラー (Scheduler): Betaステップ数 (Steps): 24 ~ 30CFG: 5.5解像度: 1024x1024以上(64の倍数で設定してください)もし不安定な点や改善の要望があれば、ぜひフィードバックをお願いします!

Comentarios

Obra de arte hecha por illustriousWAI-ZimageStyle(梦歆·明绘)

1
AI artwork featuring #The Idolmaster generated with illustriousWAI-ZimageStyle(梦歆·明绘)
Avatar image of n a
1girl, masterpiece, hijab, no hair, beautiful illustration, soft lighting, Yaya, pink hijab, goggles on head, pink scarf, white flower pin, pink and white outfit, long sleeves, pink pants, yellow belt, wristband/watch, outdoors, sky, cloud, night, building, scenery, smoke, reflection, sign, city, cityscape, skyscraper, city lights, cyberpunk, neon lights, solo, black hair, jewelry, standing, full body, shoes, indoors, necklace, striped clothes, sweater, sleeves past wrists, sneakers, white shoes, white pants, stairs, head out of frame, striped sweater, wrinkled fabric, hair ornament, brown eyes, school uniform, pink hair, flower, necktie, crossed arms, animification
n a
AI artwork generated with illustriousWAI-ZimageStyle(梦歆·明绘)
ml
The image shows an anime girl with long white hair wearing a black dress and a white cat ears on her head, standing against a white background with colorful petals scattered around her. 1girl, solo, long hair, looking at viewer, smile, open mouth, shirt, simple background, blue eyes, white background, hair ornament, animal ears, very long hair, white shirt, standing, full body, blue hair, tail, multicolored hair, white hair, :d, pantyhose, boots, hairclip, fang, streaked hair, apron, fox ears, fox tail, crossed arms, fox girl, white pantyhose, multiple tails, kitsune, kyuubi
minh lam
AI artwork generated with illustriousWAI-ZimageStyle(梦歆·明绘)
ml
The image shows a drawing of a girl with pink hair wearing a dress and a duck on her head. The background is white and there is a watermark in the bottom right corner. 1girl, solo, long hair, open mouth, simple background, blue eyes, white background, animal ears, upper body, tail, pink hair, artist name, hood, twitter username, bird, furry, eyes visible through hair, ?, furry female, asymmetrical bangs, body fur, white fur, on head, animal on head, two-tone fur, rubber duck, bird on head, purple hoodie
minh lam
AI artwork generated with illustriousWAI-ZimageStyle(梦歆·明绘)
Avatar image of n a
1girl, hijab, no_hair, beautiful_illustration, soft_lighting, yaya, pink_hijab, goggles_on_head, pink_scarf, white_flower_pin, pink_and_white_outfit, long_sleeves, pink_pants, yellow_belt, wristband, watch, outdoors, sky, cloud, no_humans, night, building, scenery, smoke, reflection, sign, city, cityscape, skyscraper, city_lights, cyberpunk, neon_lights, solo, black_hair, jewelry, standing, full_body, shoes, pants, indoors, necklace, striped_clothes, sweater, sleeves_past_wrists, sneakers, white_shoes, white_pants, stairs, head_out_of_frame, striped_sweater, wrinkled_fabric
n a
AI artwork generated with illustriousWAI-ZimageStyle(梦歆·明绘)
Avatar image of n a
1girl, masterpiece, hijab, no hair, beautiful illustration, soft lighting, Yaya, pink hijab, goggles on head, pink scarf, white flower pin, pink and white outfit, long sleeves, pink pants, yellow belt, wristband/watch, outdoors, sky, cloud, night, building, scenery, smoke, reflection, sign, city, cityscape, skyscraper, city lights, cyberpunk, neon lights, solo, black hair, jewelry, standing, full body, shoes, indoors, necklace, striped clothes, sweater, sleeves past wrists, sneakers, white shoes, white pants, stairs, head out of frame, striped sweater, wrinkled fabric, hair ornament, brown eyes, school uniform, pink hair, flower, necktie, crossed arms, animification
n a
AI artwork generated with illustriousWAI-ZimageStyle(梦歆·明绘)
Avatar image of n a
flower, outdoors, sky, day, cloud, blue sky, tree, no humans, petals, white flower, sunlight, cloudy sky, plant, building, scenery, blue flower, 1girl, solo, smile, hat, full body, brown eyes, boots, pants, capelet, yellow background, goggles, goggles on head, brown pants, goggles on headwear, pants under skirt, hijab, anime hijab girl, no hair, beautiful illustration, soft lighting, Yaya, pink hijab, pink scarf, white flower pin, pink and white outfit, long sleeves, pink pants, yellow belt, wristband/watch
n a