Uruchom lokalnie
majicmixRealistic_v7.safetensors
1.99 GB · SafeTensor · fp16 · pruned
Pobieranie obsługuje Civitai. Niektórzy twórcy wymagają najpierw zalogowania się na Civitai.
O tym modelu
STABLE DIFFUSION 1.5 · Modele bazowe
majicMIX realistic 麦橘写实 model by Merjic
Notatki twórcy
V7 is here. So far so good for me.
ASIAN ALERT!
推荐参数 Recommended Parameters for V7:
Sampler: Euler a, Euler, restart
Steps: 20~40
Hires upscaler: ESRGAN 4x or 4x-UltraSharp or 8x_NMKD-Superscale_150000_G
Hires upscale: 2+
Hires steps: 15+
Hires denoising strength: 0.05~0.5
clip skip 2
如果要修复脸部,请使用after detailer.
If your face comes out badly, use after detailer instead of face restoration.
我习惯开启Dynamic Thresholding来更好控制cfg值,1~20都可以尝试一下。
Use Dynmaic Thresholding to control CFG. You can try from 1~20.
如果要添加滤镜效果、噪点,请使用BMAB.
If you want to add noise like me, use BMAB.
v2.5 is here. Note that this is not v7, but an upgrade for v2. V7 may need to address more issues, which I am still trying to do. In the process, I have created a model worth sharing.
This model can restore the light and shadow of the original majicmix v2, but with increased realism while still keeping the basic aesthetic of the face. I have tested other face loras and they work fine. Please use adetailer and put the face lora in it.
请注意,这不是v7,而是对v2的修缮。v7可能需要突破更多问题,这个目前我还在尝试。在这个过程中我融合出一个模型,我认为也值得分享。
本模型可以还原初代majicmix的光影,但是增加写实度,脸部还是保持基本调性的审美,我测试了其他脸部lora都没问题。请使用adetailer然后把脸部lora放在里面使用。
v5对我来说不够好,对你们来说也是的,而且不够写实。所以v6很迫切需要。用Euler画特写,用euler a 画其他的。不要!不要!不要开脸部修复!用adetailer来修脸。我的例图都用了。
v6 is here. v5 is not good as I played for a while and see the results from yours. Therefore a v6 is urgent.
Use Euler for close up, and Euler a for others. Again, don't use facial restoration, use After detailer instead! All my samples used adetailer without lora.
第五版先行版来了,先把赛博永生小姐姐娜乌斯嘉融进来做个例子,也算是公测吧。
5th edtion is coming soon. I've posted a preview version with the face of nwsj.
推荐使用Euler作为采样器。
Use Euler as sampler.
听我一句劝,不要开脸部修复!
Please don't use Face Restoration!
如果要修复脸部,请使用after detailer.
If your face comes out badly, use after detailer instead.
我习惯开启Dynamic Thresholding来更好控制cfg值,1~20都可以尝试一下。
Use Dynmaic Thresholding to control CFG. You can try from 1~20.
很抱歉在之前的例图中我使用了分层的lora让大家困惑,也让大家复刻我的例图变得困难。所以新一版的例图我没有使用任何lora。想了解lora分层的可以参考:
I apologize for using lora block weight in the example images of the previous edition, which confused most of you and made it difficult for you to replicate my examples. Therefore, in the newer editions, I did not use any lora in my showcase. If you would like to learn about lora block weight, please refer to:
融合了多种模型,可以生成好看的脸部,也能有效应对暗部处理。远距离脸部需要inpaint以达成最好效果。也可以使用after detailer.
A good looking model, suitable for NSFW and dark scene (because I added noiseoffset). long-range facial detail require inpainting to achieve the best results. You can also use after detailer.
推荐关键词 recommended positive prompts: Best quality, masterpiece, ultra high res, (photorealistic:1.4), 1girl
如果想要更暗的图像 if you want darker picture, add: in the dark, deep shadow, low key, etc.
负面关键词 use and in negative prompt
I've used a bug-fixed version of DPM++ 2M Karras, you can check this out:
推荐参数Recommended Parameters:
Sampler: Euler a, Euler, DPM++ 2M Karras (bug-fixed) or DPM++ SDE Karras
Steps: 20~40
Hires upscaler: R-ESRGAN 4x+ or 4x-UltraSharp
Hires upscale: 2
Hires steps: 15
Denoising strength: 0.2~0.5
CFG scale: 6-8
clip skip 2
basic formula:
+ +
关注我的TG频道看更多例图:
SHA256
7C819B6D13663ED720C2254F4FE18373107DFEF2448D337913C8FC545640881E
ID modelu ModelTrends.ai
#1646
Zgłoś treść
Przykładowe rendery
Prompty i ustawienia udostępnione przez osoby, które wykonały te rendery na Civitai. Wybierz render, aby zobaczyć, jak powstał.
Ustawienia
Sampler
Euler a
Kroki
20
Guidance
12
Seed
3882543293
Rozmiar
512x768
Clip skip
2
Prompt
1girl,sweater,white background,
Prompt negatywny
(worst quality:2),(low quality:2),(normal quality:2),lowres,watermark,
Ustawienia
Sampler
Restart
Kroki
20
Guidance
7
Seed
4216575493
Rozmiar
512x768
Clip skip
2
Prompt
1girl,hair with bangs,black long dress,orange background,
Prompt negatywny
(worst quality:2),(low quality:2),(normal quality:2),lowres,watermark,
Ustawienia
Sampler
Restart
Kroki
30
Guidance
7
Seed
2840409752
Rozmiar
512x768
Clip skip
2
Prompt
1girl,face,white background,
Prompt negatywny
(worst quality:2),(low quality:2),(normal quality:2),lowres,watermark,
Ustawienia
Sampler
Euler a
Kroki
30
Guidance
7.5
Seed
1519084592
Rozmiar
512x768
Clip skip
2
Prompt
cat
Prompt negatywny
(worst quality:2),(low quality:2),(normal quality:2),lowres,bad anatomy,bad hands,
Ustawienia
Sampler
Euler a
Kroki
30
Guidance
7.5
Seed
1519084598
Rozmiar
512x768
Clip skip
2
Prompt
cat
Prompt negatywny
(worst quality:2),(low quality:2),(normal quality:2),lowres,bad anatomy,bad hands,
Ustawienia
Sampler
Euler a
Kroki
30
Guidance
7.5
Seed
1519084593
Rozmiar
512x768
Clip skip
2
Prompt
cat
Prompt negatywny
(worst quality:2),(low quality:2),(normal quality:2),lowres,bad anatomy,bad hands,
Ustawienia
Sampler
Restart
Kroki
32
Guidance
7
Seed
1725542165
Rozmiar
512x768
Clip skip
2
Prompt
1girl,face,white background,
Prompt negatywny
(worst quality:2),(low quality:2),(normal quality:2),lowres,watermark,
Ustawienia
Sampler
DPM++ 2M SDE Karras
Kroki
40
Guidance
9.5
Seed
2397261064
Rozmiar
1408x1664
Clip skip
2
Prompt
dark night, dark theme, heavy snowing, platform, red train, (masterpiece),((ultra-detailed)), (highly detailed CG illustration),(expressionless), (best quality:1.2), High quality texture, intricate details, detailed texture, High quality shadow, Cinematic Light, Depth of field, light source contrast, perspective,20s, (ulzzang-6500-v1.1:0.5), <lora:epi_noiseoffset2:1>, <lora:add_detail:0.8>,
Prompt negatywny
EasyNegative,paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), ng_deepnegative_v1_75t
Podobne modele
Modele AI do generowania obrazów, wideo i tekstu
majic7 to model bazowy z rodziny Stable Diffusion 1.5 wymieniony na ModelTrends.ai, katalogu tylko do odczytu otwartych modeli AI do obrazów, wideo i tekstu. Porównaj go z innymi modelami Stable Diffusion 1.5, sprawdź wynik popularności, aby zobaczyć trend, i otwórz na PirateDiffusion lub BitVector, aby wypróbować.
Więcej modeli Stable Diffusion 1.5Więcej Stable Diffusion 1.5 Modele bazoweasianrealisticbasephotoralisticbase model
Przeglądaj według rodziny modeli
Modele Text / LLM
411
Modele Anima
509
Modele Chroma
14
Modele Flux
1,071
Modele Flux 2 / Klein
1,237
Modele MiniMax H3
331
Modele Hunyuan
197
Modele Ideogram
20
Modele Krea2
674
Modele Qwen
17
Modele Qwen2
36
Modele Ltx2
150
Modele Stable Diffusion 1.5
6,465
Modele Stable Diffusion XL 1.0
15,432
Modele Zimage
804
Modele Wan
919

Model
Trends
.ai
© ModelTrends.ai
|
Wyprodukowano w Japonii
|
© 2026
