persona5 alloutattacks xl
Vergleichen
7595°
Lokal ausführen
p5_attacks_v0.2.safetensors
245 MB · SafeTensor
Downloads werden von Civitai bereitgestellt. Manche Ersteller verlangen zuerst eine Anmeldung bei Civitai.
AD
Auf Graydient installieren / ausführen
Mitgliedschaft erforderlich
<persona5-alloutattacks-xl>
Über dieses Modell
STABLE DIFFUSION XL 1.0 · LoRAs
by Fabent6991 - Persona 5 All Out Attacks (Total Attack/Execution Result Screen)
Notizen des Erstellers
Trained on animagineXLV3_v30, generate images of All Out Attacks execution scene of Persona 5.
Recommended weight: 0.8 is recommended.
(Although a higher weight generates a style more similar to the original, it tends to introduce noticeable errors. Using 0.8 provides a more balanced approach.If you want to restore the style, use 1.The first picture on the cover is 1, and the others are 0.8)
The dataset is trained at a resolution of 1152*1152, comprising 53 images.
The optimal generation resolution is 1536*864, which is the aspect ratio of almost all datasets.
Trigger words: All Out Attacks, silhouette, English text, mask, glove.
(the primary trigger word is All Out Attacks; this is my first time training the Lora style, and there is no comparative data in the dataset. During testing, it was found that adding or not adding these trigger words made little difference. Other trigger words can be added as needed.)
The labeling method involves full tagging + trigger words.
Slightly adding some character tags can help alleviate quality loss, such as red eyes, red hair.
After the training was completed, I learned that animagineXLV3_V3.1 had already been released...
===========================================================
基于animagineXLV3_v30训练,生成女神异闻录5的总攻击处刑画面图像。
推荐权重:推荐0.8。
(虽然更高的权重生成的画风更像,但是会出现明显错误,使用0.8来说更均衡。如果更想要还原画风那就使用1吧。封面第一张图是1,其他是0.8。)
数据集以1152*1152分辨率进行训练,有53张。
最佳的生成分辨率是1536*864,几乎所有数据集都是这个比例。
触发词:All Out Attacks,silhouette,english text,mask,glove (主要触发词是All Out Attacks,这是我第一次训练画风lora,数据集没有对比数据,测试时发现加不加区别不大。另外几个可以根据需要填写。)
标注方式是全标+触发词。
稍微加一点形象tag可以缓解质量损失,如red eyes,red hair。
在训练完成后,我才得知animagineXLV3_V3.1已经发布了...
Triggerwörter
silhouette
english text
glove
mask
All Out Attacks
SHA256
FCC1304AA9FA8158CC8E1203662B0D32E471379F1F43FF1EEB719ED125638BFE
ModelTrends.ai-Modell-ID
#5361
Inhalt melden
Beispielbilder
Prompts und Einstellungen, geteilt von den Leuten, die diese Bilder auf Civitai erstellt haben. Wähle ein Bild, um zu sehen, wie es entstanden ist.
Einstellungen
Sampler
DPM++ 2M Karras
Schritte
50
Guidance
4
Seed
1466659891
Größe
832x1216
Clip skip
2
Verwendetes Gewicht
0.8
Prompt
Persona 5 all out attack, Skinny, Low angle view, score_9, score_8_up, score_7_up, score_6_up, gigantic breast, source_anime, 1girl, solo, long hair, female, lips, hoop earrings,, cleavage, big breasts, shiny skin, shiny skin, shiny breast, buns, erotic smile, big sexy lips, erotic pose, breast movement, cleavage, red latex pants, slim pants, big ass, expressiveh, skinny, skinny waist, tall, sexy legs, Cartoon, shapes, , low angle, no shirt, jewelry, earrings, sleeveless, hoop earrings, red suspenders, sideboobs, no bangs, big forehead, suspenders over tits, buns, sexy lips, big sexy lips, glossy lips, hourglass body, snatched waist, long legs, tall, milf, side tilt, haughty, haughty eyes, milf face, mature face, high fashion sunglasses, red hair, sunglasses on head, sexy milf eyes, innerboobs, underboobs, long eyelashes, eyeliner, silhouette, contrast, All Out Attacks, glove, splash art, colorful splash background, red and white background, flat background, solo, persona, soejima_shigenori, buns, hips tilted, high heels, fullbody, elbow tattoos, arm tattos, waist tattoo, neck tattoo
Negativer Prompt
monochrome, score_6, score_5, score_4, source_pony, (worst quality:1.2), (low quality:1.2), (normal quality:1.2), lowres, bad anatomy, bad hands, (Integration of fingers and fingers, melting fingers), signature, watermarks, ugly, imperfect eyes, , error, extra limb, missing limbs, painting by bad-artist, 3d art, extra hands, extra fingers,
Einstellungen
Sampler
Euler a
Schritte
25
Guidance
6
Seed
421456246
Größe
1536x864
Clip skip
2
Prompt
1girl,all out attacks,silhouette,english text,Little Devil,Red hair, blond eyes,claw pose ,Close one eye,Confident smile,newest,medium quality,general,masterpiece, <lora:p5_attacks_v0.2:1>
Negativer Prompt
mask,nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name
Einstellungen
Sampler
Euler a
Schritte
25
Guidance
6
Seed
2008124230
Größe
1536x864
Clip skip
2
Prompt
1girl,all out attacks,silhouette,english text,Furina \(genshin impact\),mask,Wicked smile,newest,medium quality,general,masterpiece, <lora:p5_attacks_v0.2:0.8>
Negativer Prompt
nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name
Einstellungen
Sampler
Euler a
Schritte
25
Guidance
6
Seed
1403218635
Größe
1536x864
Clip skip
2
Prompt
1girl,all out attacks,silhouette,english text,deep green hair,blue eyes,cat girl,Wicked smile,looking at viewer,shark teeth,newest,medium quality,general,masterpiece, <lora:p5_attacks_v0.2:0.8>
Negativer Prompt
nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name
Einstellungen
Sampler
Euler a
Schritte
25
Guidance
6
Seed
4037585688
Größe
1536x864
Clip skip
2
Prompt
1boy,all out attacks,silhouette,english text,blood,holding book,red necktie ,collared shirt ,close mouth,red eyes,a faint smile on one's face,Brown hair,looking at viewer,Cream coat,White lining,pen,apple,red background,newest,medium quality,general,masterpiece, <lora:p5_attacks_v0.2:0.8>
Negativer Prompt
nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name
Einstellungen
Sampler
DPM++ 2M
Schritte
50
Guidance
4
Seed
1903183017
Größe
1216x832
Clip skip
2
Verwendetes Gewicht
0.8
Prompt
score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, masterpiece, 1boy, solo, asian face, looking at viewer, undercut hair, red eyes, persona mask with leaf shape, silhouette, english text, glove, mask, All Out Attacks, black and green color
Negativer Prompt
worst quality, low quality, normal quality, lowres, low details, bad photo, bad photography, bad art:1.4),
Einstellungen
Sampler
Euler a
Schritte
30
Guidance
7
Seed
115014733645209
Größe
1024x1024
Prompt
chibi, 1man, anime, male, dark very short hair, floating hair, sliver eyes, upper body,middle ,sitting on toliet bowl,eating popcorn,moon surface,shocking
futuristic, sci-fi, space-themed, astronaut
galaxy ,colorful meteor shower
Negativer Prompt
civit_nsfw, worst quality, low quality, low score, bad score, average score,
bad anatomy, bad proportion, bad hands, missing finger,
Ähnliche Modelle
KI-Modelle für Bild-, Video- und Texterzeugung
persona5 alloutattacks xl ist ein LoRA für die Familie Stable Diffusion XL 1.0 und wird auf ModelTrends.ai gelistet, einem reinen Lesekatalog für Open-Source-KI-Modelle für Bild, Video und Text. Vergleiche es mit anderen Stable Diffusion XL 1.0-Modellen, prüfe den Hitzewert, um den Trend zu sehen, und öffne es auf PirateDiffusion oder BitVector, um es auszuprobieren.
Weitere Stable Diffusion XL 1.0-ModelleWeitere Stable Diffusion XL 1.0 LoRAsponytypeanimegamingartstylesstyleall out attackspersona 5game
Nach Modellfamilie stöbern
Text / LLM-Modelle
411
Anima-Modelle
509
Chroma-Modelle
14
Flux-Modelle
1,071
Flux 2 / Klein-Modelle
1,237
MiniMax H3-Modelle
331
Hunyuan-Modelle
197
Ideogram-Modelle
20
Krea2-Modelle
674
Qwen-Modelle
17
Qwen2-Modelle
36
Ltx2-Modelle
150
Stable Diffusion 1.5-Modelle
6,465
Stable Diffusion XL 1.0-Modelle
15,432
Zimage-Modelle
804
Wan-Modelle
919

Model
Trends
.ai
© ModelTrends.ai
|
Made in Japan
|
© 2026
