Model
Trends
.ai
Model
Trends
.ai
najlepsze otwarte modele AI
Uruchom lokalnie
majicmixRealistic_v1.safetensors
2.24 GB · SafeTensor · fp16 · pruned
Pobieranie obsługuje Civitai. Niektórzy twórcy wymagają najpierw zalogowania się na Civitai.
O tym modelu
STABLE DIFFUSION 1.5 · Modele bazowe
Autor
Merjic
na Civitai
majicMIX realistic v6 by Merjic Majic Realistic Version 6 is a remake of version 5 since the author decided that 5 isn't realistic enough. It's great at creating beautiful Asian portraits. Similar to Chilloutmix, it can be used as a base to interact with LoRas. A few tips: # It doesn't need complicated prompts, the most natural look is reachable with simple prompts. # Recommended settings by the author: /sampler:k_euler (remove '\') /Steps: 20~40 /guidance:6-8 /parser:new /clipskip:2 # Recommeneded prompts: - positive prompts: Best quality, masterpiece, ultra high res, (photorealistic:1.4), 1girl - negative prompts: [(worst quality:2), (low quality:2), (normal quality:2), lowres, watermark, monochrome] - IMPORTANT! If you use style or recipe remove the weight:2 or the quality may drop considerably. - f you want darker picture, add: in the dark, deep shadow, low key
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：
3,573 pobrań · 184 polubień na Civitai
SHA256
A7A000AD88470511B286FB2388B5CD4D59E525A1B08C0BB256B0E833913B1C18
ID modelu ModelTrends.ai
#6126
Zgłoś treść
Przykładowe rendery
Prompty i ustawienia udostępnione przez osoby, które wykonały te rendery na Civitai. Wybierz render, aby zobaczyć, jak powstał.
Ustawienia
Sampler
DPM++ 2M Karras Test
Kroki
30
Guidance
7
Seed
4066203716
Rozmiar
1024x1536
Clip skip
2
Prompt
Best quality, masterpiece, ultra high res, (photorealistic:1.4), (nsfw), <lora:Cnbeauty7_v10:0.2>,<lora:englishdolllikeness_v10:0.2>, 1girl, standing and playing golf, 1boy, father, old father,(golf course, golf club, sun ray), oversize white T-shirt, shirt lift, (gray Sweatpants:1.05), fullbody:0.8, smile:0.6, looking up, (Supermodel figure, adolescent ), makeup, perfect face, (beautiful face),(godness), (sexy pose), (beautiful natural breasts),(white_skin), (shiny skin:1.1), wide hips,(sexy lips), lifelike, (realistic, photorealistic:1.2),(fullbody shot), High ponytail,long hair, Golf course background, light on the face, realistic light reflection, Ambient lighting, depth of field,
Prompt negatywny
EasyNegative, badhandv4, ng_deepnegative_v1_75t, bad-artist, loli, skin spots, acnes, skin blemishes, (text:1.1, watermark:1.1, signature:1.1), (monochrome, grayscale), armpit hair, selfie,
Ustawienia
Sampler
DPM++ 2M Karras Test
Kroki
30
Guidance
7
Seed
3678267020
Rozmiar
512x683
Clip skip
2
Prompt
Best quality, masterpiece, ultra high res, (photorealistic:1.4), 1girl, white glowing skin, deep shadow
Prompt negatywny
ng_deepnegative_v1_75t, badhandv4, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, normal quality, ((monochrome)), ((grayscale)) nsfw
Ustawienia
Sampler
DPM++ 2M Karras Test
Kroki
30
Guidance
6.5
Seed
482888781
Rozmiar
512x683
Clip skip
2
Prompt
Best quality, masterpiece, ultra high res, (photorealistic:1.4), 1girl, in the dark
Prompt negatywny
ng_deepnegative_v1_75t, badhandv4, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, normal quality, ((monochrome)), ((grayscale))
Ustawienia
Sampler
DPM++ 2M Karras Test
Kroki
30
Guidance
6.5
Seed
603548336
Rozmiar
512x683
Clip skip
2
Prompt
Best quality, masterpiece, ultra high res, (photorealistic:1.4), 1girl, in the dark, deep shadow, low key, offshoulder, white dress
Prompt negatywny
ng_deepnegative_v1_75t, badhandv4, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, normal quality, ((monochrome)), ((grayscale))
Ustawienia
Sampler
Euler a
Kroki
30
Guidance
7
Seed
3540071697
Rozmiar
512x683
Clip skip
2
Prompt
Best quality, masterpiece, ultra high res, (photorealistic:1.4), 1girl, solo, blonde long hair, angel halo, white glowing skin, angelic, golden colored detailed angel costume, glowing light, angel holding big book, wings, feathers, deep shadow
Prompt negatywny
ng_deepnegative_v1_75t, badhandv4, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, normal quality, ((monochrome)), ((grayscale)) nsfw
Ustawienia
Sampler
DPM++ 2M Karras Test
Kroki
30
Guidance
7
Seed
895487672
Rozmiar
512x683
Clip skip
2
Prompt
Best quality, masterpiece, ultra high res, (photorealistic:1.4), in the dark, 1girl, solo, blonde long hair, angel halo, white glowing skin, angelic, wings, feathers, deep shadow, holding a candle, candle light
Prompt negatywny
ng_deepnegative_v1_75t, badhandv4, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, normal quality, ((monochrome)), ((grayscale)) nsfw
Ustawienia
Sampler
DPM++ 2M Karras Test
Kroki
30
Guidance
6.5
Seed
1972435232
Rozmiar
512x683
Clip skip
2
Prompt
Best quality, masterpiece, ultra high res, (photorealistic:1.4), 1girl, in the dark
Prompt negatywny
ng_deepnegative_v1_75t, badhandv4, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, normal quality, ((monochrome)), ((grayscale))
Ustawienia
Sampler
DPM++ 2M Karras Test
Kroki
30
Guidance
6
Seed
549431491
Rozmiar
512x683
Clip skip
2
Prompt
8k ultra high res, beautiful and aesthetic, masterpiece, best quality, (photorealistic:1.4), in the dark, deep shadow, low key, upper body, 1girl, inside a coffee shop, shy smile, ponytail, sweater and red scarf, black and white photography, fashion photography, bokeh, depth of field:1.3
Prompt negatywny
ng_deepnegative_v1_75t, badhandv4, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, normal quality, ((big breast))
Modele AI do generowania obrazów, wideo i tekstu
majic6 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.
Przeglądaj według rodziny modeli
Przeglądaj wszystkie modele