基本上是我之前融合模型的融合 basically a mix of my previous mix
majicMIX realistic - v4 | Stable Diffusion Checkpoint | Civitai
majicMIX fantasy - v2.0 | Stable Diffusion Checkpoint | Civitai
这个模型风格炸裂,远距离脸部需要inpaint以达成最好效果,使用adetailer.
This model is strongly stylized in creativity, but long-range facial detail require inpainting to achieve the best results. Use Adetailer.
请参考我的prompt来使用
recommended positive prompts: official art, unity 8k wallpaper, ultra detailed, beautiful and aesthetic, beautiful, masterpiece, best quality, (zentangle, mandala, tangle, entangle)
use ng_deepnegative_v1_75t and badhandv4 in negative
脸部修复方法 to inpaint the face:inpaint-->only masked-->set to 512x512-->Denoising strength:0.2~0.5
我的TG频道可以看到更多例图 https://t.me/majic_NSFW
Description
FAQ
Comments (15)
Has anything changed in the new version?
大佬你的图里面的<lora:Song_HanFu:0.5>是哪个模型呀?求分享呜呜
会不会是汉服宋风?
汉服 宋的风格,c站可以搜的得到
为什么生成的人脸上和身上都有雀斑、黑痣?怎么才能弄干净
使用模型生成时报错
Loading weights [53a24db033] from E:\yang\stable-diffusion-webui\models\Stable-diffusion\majicmixLux_v2.safetensors
Applying optimization: Doggettx... done.
Weights loaded in 4.9s (calculate hash: 2.4s, load weights from disk: 0.5s, apply weights to model: 0.6s, move model to device: 1.2s).
Error completing request
Arguments: ('task(fa6fdgvg6y7z2t9)', '1girl among colorful vanilla flowers, pale skin, black hair, black eyes, (unity 8k wallpaper, ultra detailed, masterpiece, best quality, official art, beautiful and aesthetic:1.2)', 'ng_deepnegative_v1_75t, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, normal quality, ((monochrome)), ((grayscale)), (badhandv4)', [], 20, None, False, False, 1, 2, 7, 2455051963.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, 0, '', '', [], 0, <scripts.controlnet_ui.controlnet_ui_group.UiControlNetUnit object at 0x00000219C34C88B0>, False, False, 'positive', 'comma', 0, False, False, '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, 0, None, None, False, 50) {}
Traceback (most recent call last):
File "E:\yang\stable-diffusion-webui\modules\call_queue.py", line 57, in f
res = list(func(*args, **kwargs))
File "E:\yang\stable-diffusion-webui\modules\call_queue.py", line 37, in f
res = func(*args, **kwargs)
File "E:\yang\stable-diffusion-webui\modules\txt2img.py", line 26, in txt2img
sampler_name=sd_samplers.samplers[sampler_index].name,
TypeError: list indices must be integers or slices, not NoneType
anybody knows where to find lora:DarkAngelTileStyle ????
Is there a free service that permits nsfw that I can run this on?
yes, search Automatic 1111 for Stable Diffusion
google "16GB GPU"
Beauty 😍😍
SD 1.6 畫風大不同喔
Details
Files
majicmixLux_v2.safetensors
Mirrors
majicmixLux_v2.safetensors
majicmixLux_v2.safetensors
majicmixLux_v2.safetensors
MajicMix_Lux.safetensors
majicmixLux_v2.safetensors
majicmixLux_v2.safetensors
MajicMix_Lux.safetensors
majicmixLux_v2.safetensors
majicmixLux_v2.safetensors
majicMIX lux_v2.safetensors
majicmixLux_v2.safetensors
majicmixLux_v2.safetensors
majicmixLux_v2.safetensors
majicmixLux_v2.safetensors
majicmixLux_v2.safetensors
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.

