Model
Trends
.ai
Model
Trends
.ai
los mejores modelos de IA de código abierto
Ejecutar en local
catman.safetensors
72 MB · SafeTensor
Las descargas las sirve Civitai. Algunos creadores piden iniciar sesión en Civitai primero.
Sobre este modelo
STABLE DIFFUSION 1.5 · LoRAs
Creado por
dainichi_huoguo
en Civitai
Notas del creador
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,
Palabras de activación
maomi
4,220 descargas · 428 me gusta en Civitai
SHA256
BD9E35C5BA6405C60FE165451E11122BC9FAF696BCF22A73CF94E7B90837643D
ID de modelo de ModelTrends.ai
#771
Denunciar contenido
Renders de ejemplo
Prompts y ajustes compartidos por quienes hicieron estos renders en Civitai. Elige un render para ver cómo se hizo.
Ajustes
Sampler
DPM++ SDE Karras
Pasos
30
Guidance
7
Semilla
1555863099
Tamaño
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,
Prompt negativo
(EasyNegative:1.2),badhandv4,ng_deepnegative_v1_75t,worst quality,low quality,monochrome,
Ajustes
Sampler
DPM++ SDE Karras
Pasos
30
Guidance
7
Semilla
1195576729
Tamaño
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,
Prompt negativo
(EasyNegative:1.2),badhandv4,ng_deepnegative_v1_75t,worst quality,low quality,monochrome,
Ajustes
Tamaño
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.
Prompt negativo
lazyneg
Ajustes
Sampler
DPM++ SDE Karras
Pasos
30
Guidance
7
Semilla
2345528969
Tamaño
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,
Prompt negativo
(EasyNegative:1.2),badhandv4,ng_deepnegative_v1_75t,worst quality,low quality,monochrome,
Ajustes
Sampler
DPM++ SDE Karras
Pasos
30
Guidance
7
Semilla
2380459891
Tamaño
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,
Prompt negativo
(EasyNegative:1.2),badhandv4,ng_deepnegative_v1_75t,worst quality,low quality,monochrome,
Ajustes
Sampler
DPM++ SDE Karras
Pasos
30
Guidance
7
Semilla
2367801709
Tamaño
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
Prompt negativo
(EasyNegative:1.2),badhandv4,ng_deepnegative_v1_75t,worst quality,low quality,monochrome,
Ajustes
Sampler
DPM++ SDE Karras
Pasos
30
Guidance
7
Semilla
4204446260
Tamaño
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,
Prompt negativo
(EasyNegative:1.2),badhandv4,ng_deepnegative_v1_75t,worst quality,low quality,monochrome,
Ajustes
Sampler
DPM++ SDE Karras
Pasos
20
Guidance
7
Semilla
75206587
Tamaño
768x768
Clip skip
2
Prompt
(best quality, masterpiece:1.2),maomi,in the classroom,<lora:catman:0.7>,Maid dress,maine cat,
Prompt negativo
(EasyNegative:1.2), badhandv4,ng_deepnegative_v1_75t,worst quality, low quality, monochrome
Modelos de IA para generar imagen, vídeo y texto
catman es un LoRA para la familia Stable Diffusion 1.5 listado en ModelTrends.ai, un catálogo de solo lectura de modelos de IA de imagen, vídeo y texto de código abierto. Compáralo con otros modelos Stable Diffusion 1.5, consulta su puntuación de calor para ver su tendencia y ábrelo en PirateDiffusion o BitVector para probarlo.
Explorar por familia de modelos
Ver todos los modelos