【CHECKPOINT】MeinaMix二次元女孩美娜meinamix_meinaV9[EAC6C08A19]

奶味小可爱

名称：meinamix_meinaV9.safetensors
程序版本：SD 1.5
模型大小：3.74GB
备注：
Enable Quantization in K samplers.
Hires.fix is needed for prompts where the character is far away in order to make decent images, it drastically improve the quality of face and eyes!
---------------------------------------------
Recommended parameters:
Sampler: Euler a: 40~60 steps.
Sampler: DPM++ SDE Karras: 30~60 steps.
CFG Scale: 7.
Resolutions: 512x768, 512x1024 for Portrait!
Resolutions: 768x512, 1024x512, 1536x512 for Landscape!
Hires.fix: R-ESRGAN 4x+Anime6b, with 10 steps at 0.1 up to 0.3 denoising.
Clip Skip: 2.
Negatives: ' (worst quality:2, low quality:2), (zombie, sketch, interlocked fingers, comic), '.
在 K 采样器中启用量化。
Hires.fix 需要用于角色远离的提示，以便制作出体面的图像，它大大提高了面部和眼睛的质量！
---------------------------------------------
推荐参数：
Sampler：Euler a：40~60步。
Sampler：DPM++ SDE Karras：30~60步。
CFG Scale：7。
分辨率：512x768、512x1024 为肖像！
分辨率： 768x512， 1024x512， 1536x512 为风景！
Hires.fix：R-ESRGAN 4x+Anime6b，在 10.0 到 1.0 降噪时有 3 个步骤。
Clip Skip：2。
底片：' （最差质量：2，低质量：2），（僵尸，素描，互锁手指，漫画）， '
--------------------------------------------------------------------------------

Hash	parameter
SHA256	EAC6C08A199C4953F80AE5B4EA5F9B2D88C7F3C6F2546E14A57851E3E4A1C5CB
CRC32	9B43B52B
BLAKE3	16BCE9E1198433C2A8261BC896FBCAF521FF5B9A24B210BFBD1E5256589102E9
AUTOV1	2EC66AB0
AUTOV2	EAC6C08A19

作品展示：

Generation Data：

1. upper body, 1girl, white hair, ponytail, purple eyes, (ninja), short sword, medium breats ,scarf, wallpaper, magic circle background, light particles, blue fire,
   
2. Negative prompt: (worst quality:2, low quality:2), (zombie, sketch, interlocked fingers, comic),
   
3. Size: 512x1024, Seed: 1400040347, Model: Meina V9 - baked VAE, Steps: 40, Sampler: DPM++ SDE Karras, CFG scale: 7, Clip skip: 2, Model hash: eac6c08a19, Hires steps: 10, Hires upscale: 2, Hires upscaler: R-ESRGAN 4x+ Anime6B, Denoising strength: 0.3

复制代码

Generation Data：

1. 1girl, (big ben:1.2), (crowd:1.2), <lora:violetEvergarden_v10:1>, violet_evergarden, blue_eyes, medium_breasts, blonde_hair, (gothic_dress:1.4), (earrings:1.2), hair_ribbon, London, holding tote bag, smile, gem
   
2. Negative prompt: EasyNegative, lowres, text, bad anatomy, jpeg artifacts, signature, watermark, username, artist name, trademark, bad feet, night
   
3. Size: 512x768, Seed: 619606590, Model: meinamix_meinaV9, Steps: 30, Sampler: DPM++ SDE Karras, CFG scale: 4, Clip skip: 2, Model hash: eac6c08a19, Hires upscale: 2, Hires upscaler: SwinIR_4x, Denoising strength: 0.55

复制代码

Generation Data：

1. (((masterpiece))), (((best quality))), ((((look up)))), hand in pocket, 1girl, shoes, goggles, gun, weapon, standing, sneakers, twintails, jacket, blonde hair, building, looking at viewer, goggles on head, bag, outdoors, long sleeves, rifle, shorts, full body, bangs, coat, city, backpack, solo, short hair, holding, mask, zipper, yellow eyes, open clothes, white coat, eyewear on head, brown eyes, skyscraper, solo focus, white jacket, hands in pockets, mouth mask, arm up, covered mouth, brown hair, bare legs, high collar, assault rifle, turtleneck,
   
2. Negative prompt: sketch, duplicate, ugly, huge eyes, text, logo, monochrome, worst face, (bad and mutated hands:1.3), (worst quality:2.0), (low quality:2.0), (blurry:2.0), horror, geometry, bad_prompt, (bad hands), (missing fingers), multiple limbs, bad anatomy, (interlocked fingers:1.2), Ugly Fingers, (extra digit and hands and fingers and legs and arms:1.4), ((2girl)), (deformed fingers:1.2), (long fingers:1.2),(bad-artist-anime), bad-artist, bad hand, extra legs, nipples,nsfw,
   
3. ENSD: 31337, Size: 560x1000, Seed: 401057089, Model: meinamix_meinaV8, Steps: 28, Sampler: DPM++ 2M Karras, CFG scale: 7.5, Model hash: 30953ab0de, Hires steps: 10, Hires upscale: 2, Hires upscaler: R-ESRGAN 4x+ Anime6B, ControlNet 0 Model: control_v11f1p_sd15_depth [cfd03158], Denoising strength: 0.55, ControlNet 0 Weight: 1, ControlNet 0 Enabled: True, ControlNet 0 Ending Step: 0.53, ControlNet 0 Resize Mode: Crop and Resize, ControlNet 0 Control Mode: My prompt is more important, ControlNet 0 Preprocessor: depth_zoe, ControlNet 0 Pixel Perfect: True, ControlNet 0 Starting Step: 0, ControlNet 0 Preprocessor Parameters: "(512, 64, 64)"

复制代码

Generation Data：

1. <lora:shukezouma_v1_1:0.8>, masterpiece, best quality, ((willow trees)), upper body, 1girl, standing, hanfu, detailed eyes, medium breasts, peaceful, looking at viewer, black hair, <lora:MoXinV1:0.6>,
   
2. Negative prompt: badhandv4, (worst quality:2), (low quality:2), error, (bad hands:1.2), (bad fingers), extra eyebrows, sketch, bad anatomy, text
   
3. ENSD: 31337, Size: 720x1280, Seed: 4015453017, Model: meinamix_meinaV9, Steps: 30, Sampler: DPM++ SDE Karras, CFG scale: 7, Clip skip: 2, Model hash: eac6c08a19

复制代码

Generation Data：

1. ultra 8k cg,  watercolor, picture-perfect face, flawless, clean, masterpiece, professional artwork, famous artwork, cinematic lighting, cinematic bloom, 1 adult, fullbody, white hair, (colorful suit:1.5), sheath, (holding sword:1.3), unsheathing, (on the top of mountain:1.5), dragon, (holding sword:1.3), ((dramatic lighting)),sharp focus, open kimono, fancy trench coat,fighting ,colorful background, flame
   
2. Negative prompt: (poorly drawn face:1.4), (worst quality, low quality:1.3), logo, watermark, text, (fused fingers), (simple background: 1.5), (too many fingers),crossed fingers, (low quality, worst quality:1.4),(bad_prompt_version2:0.8), (monochrome:1.1), extra fingers,blurry, ((bad anatomy)), (((bad proportions))),extra legs, missing legs, extra feet, missing feet, mal-formed legs, mal-formed feet, extra toes, missing toes, extra fingers, missing fingers, fused fingers, extra arms, missing arms, extra hands, missing hands, heavy, fat, pointy ear
   
3. Size: 512x512, Seed: 3748454699, Model: meinamix_meinaV9, Steps: 30, Sampler: DPM++ SDE Karras, CFG scale: 7, Model hash: eac6c08a19, Hires upscale: 2, AddNet Enabled: True, AddNet Model 1: Battojutsuswing(015898a20de8), AddNet Model 2: MoXinV1(17cd20c7b6ea), AddNet Model 3: Watercolor(33ac03c37235), Hires upscaler: Latent, AddNet Module 1: LoRA, AddNet Module 2: LoRA, AddNet Module 3: LoRA, AddNet Weight A 1: 0.5, AddNet Weight A 2: 0.45, AddNet Weight A 3: 0.8, AddNet Weight B 1: 0.5, AddNet Weight B 2: 0.45, AddNet Weight B 3: 0.8, Denoising strength: 0.7

复制代码

下载地址：

游客，如果您要查看本帖隐藏内容请回复