Lokal ausführen
catman.safetensors
72 MB · SafeTensor
Downloads werden von Civitai bereitgestellt. Manche Ersteller verlangen zuerst eine Anmeldung bei Civitai.
Über dieses Modell
STABLE DIFFUSION 1.5 · LoRAs
Notizen des Erstellers
你可以换成任意的动物，但是训练集是猫，会和猫融合（You can change it to any animal you want, but the training set is a cat, and it fuses with a cat）
推荐分辨率：512*512 768*768 512*768
推荐二次元采样方法：Euler a ，DPM++ 2M Karras ，DPM++ 2S a Karras，
推荐写实采样方法：DPM++ SDE Karras，DPM++ 2M SDE Karras，
和别的LORA搭配使用也不错~
如果开启高清修复，出图效果会更好~
高清修复推荐设置：
二次元推荐放大算法：R-ESRGAN 4x+ Anime6B 放大倍数1.5-2倍
写实推荐放大算法：R-ESRGAN 4x+
重绘幅度：0.4-0.6
推荐二次元大模型:：sdhk_v30.preview，meinamix_meinaV11.preview，kidsmix_v10.preview，CounterfeitV30_v30.preview，darkSushiMixMix_225D.preview ，二次元模型基本都可以。
推荐写实大模型: revAnimated_v122.preview，realisticVisionV51_v51VAE，xxmix9realistic_v40.preview，
Lora触发词：maomi
Lora推荐权重：0.6-1.0
负面提示词：(EasyNegative:1.2),badhandv4,ng_deepnegative_v1_75t,worst quality,low quality,monochrome,
正向提示词： (best quality, masterpiece:1.2),maomi
我的b站： 抖音名字：带你吃火锅
Recommended resolution: 512*512 768*768 512*768
Recommended Secondary Sampling Methods: Euler a , DPM++ 2M Karras, DPM++ 2S a Karras，
Recommended realistic sampling method: DPM++ SDE Karras，DPM++ 2M SDE Karras，
It is also good to use with other LORA.
If you turn on HD Repair, the result will be better.
Recommended settings for HD restoration:
Secondary recommended zoom algorithm: R-ESRGAN 4x+ Anime6B Magnification 1.5-2x
Realistic Recommended Zoom Algorithm: R-ESRGAN 4x+
Redraw amplitude: 0.4-0.6
Recommended quadratic large models : sdhk_v30.preview, meinamix_meinaV11.preview, kidsmix_v10.preview, CounterfeitV30_v30.preview, darkSushiMixMix_225D.preview Binary models are basically fine.
Recommended realistic large models: revAnimated_v122.preview，realisticVisionV51_v51VAE，xxmix9realistic_v40.preview，
Lora trigger word: maomi
Lora recommendation weight: 0.6-1.0
Negative Tip Words: (EasyNegative:1.2),badhandv4,ng_deepnegative_v1_75t,worst quality,low quality,monochrome,
Positive Tip Words: (best quality, masterpiece:1.2),maomi,
Triggerwörter
maomi
SHA256
BD9E35C5BA6405C60FE165451E11122BC9FAF696BCF22A73CF94E7B90837643D
ModelTrends.ai-Modell-ID
#771
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++ SDE Karras
Schritte
30
Guidance
7
Seed
1555863099
Größe
512x768
Clip skip
2
Prompt
HDR,UHD,8K,Highly detailed,realistic,photo-realistic:1.37),best quality,masterpiece,<lora:catman:0.75>,maomi,blurry background,blurry,sunglasses,hat,hands in pockets,coat,standing,shirt,solo,outdoors,shoes,full body,pink headwear,depth of field,open clothes,
Negativer Prompt
(EasyNegative:1.2),badhandv4,ng_deepnegative_v1_75t,worst quality,low quality,monochrome,
Einstellungen
Sampler
DPM++ SDE Karras
Schritte
30
Guidance
7
Seed
1195576729
Größe
512x768
Clip skip
2
Prompt
HDR,UHD,8K,Highly detailed,realistic,photo-realistic:1.37),best quality,masterpiece,<lora:catman:0.75>,maomi,lovely,night,lantern,japanese clothing,beautiful detailed pampas grass field, open hakama, surrounded by floating sakura, yellow full moon, beautiful detailed dark midnight sky, messy white long hair,
Negativer Prompt
(EasyNegative:1.2),badhandv4,ng_deepnegative_v1_75t,worst quality,low quality,monochrome,
Einstellungen
Größe
1024x1536
Prompt
lazypos, perfect anatomy, absolutely eye-catching, ambient occlusion, amazing quality, best quality, very awa,
1girl, solo, Blushing, long hair, looking at viewer, parted lips, blonde hair, red eyes, cute, holding cat, Cherry blossom tree, tower, river pink ribbon. She wears a pastel blue coat and carries a floral tote bag, smiling brightly as she walks through a cherry blossom path in full bloom. Soft petals fall around her, and golden sunlight filters through the pink canopy, creating a warm and dreamy spring atmosphere with gentle depth and glow.
Negativer Prompt
lazyneg
Einstellungen
Sampler
DPM++ SDE Karras
Schritte
30
Guidance
7
Seed
2345528969
Größe
512x768
Clip skip
2
Prompt
HDR,UHD,8K,Highly detailed,realistic,photo-realistic:1.37),best quality,<lora:catman:0.75>,masterpiece,chef,cooking in the kitchen,
Negativer Prompt
(EasyNegative:1.2),badhandv4,ng_deepnegative_v1_75t,worst quality,low quality,monochrome,
Einstellungen
Sampler
DPM++ SDE Karras
Schritte
30
Guidance
7
Seed
2380459891
Größe
512x768
Clip skip
2
Prompt
HDR,UHD,8K,Highly detailed,realistic,photo-realistic:1.37),best quality,<lora:catman:0.75>,masterpiece,maomi,instrument,hat,music,guitar,tongue,solo,playing instrument,open mouth,shirt,
Negativer Prompt
(EasyNegative:1.2),badhandv4,ng_deepnegative_v1_75t,worst quality,low quality,monochrome,
Einstellungen
Sampler
DPM++ SDE Karras
Schritte
30
Guidance
7
Seed
2367801709
Größe
512x768
Clip skip
2
Prompt
HDR,UHD,8K,Highly detailed,realistic,photo-realistic:1.37),best quality,masterpiece,<lora:catman:0.75>,maomi,standing,solo,full body,toddler,coffee cup
Negativer Prompt
(EasyNegative:1.2),badhandv4,ng_deepnegative_v1_75t,worst quality,low quality,monochrome,
Einstellungen
Sampler
DPM++ SDE Karras
Schritte
30
Guidance
7
Seed
4204446260
Größe
512x768
Clip skip
2
Prompt
HDR,UHD,8K,Highly detailed,best quality,masterpiece,<lora:catman:0.7>,maomi,(cyberpunk city:1.2),hood,bag,backpack,looking at viewer,walking,blurry background,solo,white footwear,pants,blurry,hood up,sky,outdoors,<lora:BlueAP-CIVIT(0,8):0.6>,in the style of BlueAP,glowing eyes,
Negativer Prompt
(EasyNegative:1.2),badhandv4,ng_deepnegative_v1_75t,worst quality,low quality,monochrome,
Einstellungen
Sampler
DPM++ SDE Karras
Schritte
20
Guidance
7
Seed
75206587
Größe
768x768
Clip skip
2
Prompt
(best quality, masterpiece:1.2),maomi,in the classroom,<lora:catman:0.7>,Maid dress,maine cat,
Negativer Prompt
(EasyNegative:1.2), badhandv4,ng_deepnegative_v1_75t,worst quality, low quality, monochrome
Ähnliche Modelle
KI-Modelle für Bild-, Video- und Texterzeugung
catman ist ein LoRA für die Familie Stable Diffusion 1.5 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 1.5-Modellen, prüfe den Hitzewert, um den Trend zu sehen, und öffne es auf PirateDiffusion oder BitVector, um es auszuprobieren.
Weitere Stable Diffusion 1.5-ModelleWeitere Stable Diffusion 1.5 LoRAsanimalscreaturesartstylesstyle
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