Upload README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,106 @@
|
|
| 1 |
---
|
| 2 |
license: creativeml-openrail-m
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: creativeml-openrail-m
|
| 3 |
+
tags:
|
| 4 |
+
- coreml
|
| 5 |
+
- stable-diffusion
|
| 6 |
+
- text-to-image
|
| 7 |
---
|
| 8 |
+
# Core ML Converted Model:
|
| 9 |
+
|
| 10 |
+
- This model was converted to [Core ML for use on Apple Silicon devices](https://github.com/apple/ml-stable-diffusion). Conversion instructions can be found [here](https://github.com/godly-devotion/MochiDiffusion/wiki/How-to-convert-ckpt-or-safetensors-files-to-Core-ML).
|
| 11 |
+
- Provide the model to an app such as **Mochi Diffusion** [Github](https://github.com/godly-devotion/MochiDiffusion) / [Discord](https://discord.gg/x2kartzxGv) to generate images.
|
| 12 |
+
- `split_einsum` version is compatible with all compute unit options including Neural Engine.
|
| 13 |
+
- `original` version is only compatible with `CPU & GPU` option.
|
| 14 |
+
- Custom resolution versions are tagged accordingly.
|
| 15 |
+
- The `vae-ft-mse-840000-ema-pruned.ckpt` VAE is embedded into the model.
|
| 16 |
+
- This model was converted with a `vae-encoder` for use with `image2image`.
|
| 17 |
+
- This model is `fp16`.
|
| 18 |
+
- Descriptions are posted as-is from original model source.
|
| 19 |
+
- Not all features and/or results may be available in `CoreML` format.
|
| 20 |
+
- This model does not have the [unet split into chunks](https://github.com/apple/ml-stable-diffusion#-converting-models-to-core-ml).
|
| 21 |
+
- This model does not include a `safety checker` (for NSFW content).
|
| 22 |
+
- This model can be used with ControlNet.
|
| 23 |
+
|
| 24 |
+
<br>
|
| 25 |
+
|
| 26 |
+
# majicmixRealistic_v6_cn:
|
| 27 |
+
Source(s): [CivitAI](https://civitai.com/models/43331/majicmix-realistic)<br>
|
| 28 |
+
|
| 29 |
+
Sponsors:
|
| 30 |
+
|
| 31 |
+
PirateDiffusion.com is a proud sponsor of MajicMix. Use it on your mobile with 750 LoRAs, +100 checkpoints, inpaint, controlnet. 7-Day risk-free trial at: https://PirateDiffusion.com
|
| 32 |
+
|
| 33 |
+
SinkIn.ai hosts the best Stable Diffusion models on fast GPUs. You can run MajicMIX Realistic at: https://sinkin.ai/m/yBG2r9O
|
| 34 |
+
|
| 35 |
+
## 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。
|
| 36 |
+
|
| 37 |
+
## v6 is here. v5 is not good as I played for a while and see the results from yours. Therefore a v6 is urgent.
|
| 38 |
+
|
| 39 |
+
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.
|
| 40 |
+
|
| 41 |
+
推荐使用Euler作为采样器。
|
| 42 |
+
|
| 43 |
+
Use Euler as sampler.
|
| 44 |
+
|
| 45 |
+
听我一句劝，不要开脸部修复！
|
| 46 |
+
|
| 47 |
+
Please don't use Face Restoration!
|
| 48 |
+
|
| 49 |
+
如果要修复脸部，请使用after detailer.
|
| 50 |
+
|
| 51 |
+
If your face comes out badly, use after detailer instead.
|
| 52 |
+
|
| 53 |
+
https://github.com/Bing-su/adetailer
|
| 54 |
+
|
| 55 |
+
我习惯开启Dynamic Thresholding来更好控制cfg值，1~20都可以尝试一下。
|
| 56 |
+
|
| 57 |
+
Use Dynmaic Thresholding to control CFG. You can try from 1~20.
|
| 58 |
+
|
| 59 |
+
https://github.com/mcmonkeyprojects/sd-dynamic-thresholding
|
| 60 |
+
|
| 61 |
+
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.
|
| 62 |
+
|
| 63 |
+
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.
|
| 64 |
+
|
| 65 |
+
推荐关键词 recommended positive prompts: Best quality, masterpiece, ultra high res, (photorealistic:1.4), 1girl
|
| 66 |
+
|
| 67 |
+
如果想要更暗的图像 if you want darker picture, add: in the dark, deep shadow, low key, etc.
|
| 68 |
+
|
| 69 |
+
负面关键词 use ng_deepnegative_v1_75t and badhandv4 in negative prompt
|
| 70 |
+
|
| 71 |
+
I've used a bug-fixed version of DPM++ 2M Karras, you can check this out: https://civitai.com/models/35966/dpm-2m-alt-karras-sampler
|
| 72 |
+
|
| 73 |
+
## 推荐参数 Recommended Parameters:
|
| 74 |
+
|
| 75 |
+
Sampler: Euler a, Euler, DPM++ 2M Karras (bug-fixed) or DPM++ SDE Karras
|
| 76 |
+
|
| 77 |
+
Steps: 20~40
|
| 78 |
+
|
| 79 |
+
Hires upscaler: R-ESRGAN 4x+ or 4x-UltraSharp
|
| 80 |
+
|
| 81 |
+
Hires upscale: 2
|
| 82 |
+
|
| 83 |
+
Hires steps: 15
|
| 84 |
+
|
| 85 |
+
Denoising strength: 0.2~0.5
|
| 86 |
+
|
| 87 |
+
CFG scale: 6-8
|
| 88 |
+
|
| 89 |
+
clip skip 2
|
| 90 |
+
|
| 91 |
+
脸部修复的方法 to inpaint the face: inpaint-->only masked-->set to 512x512-->Denoising strength:0.2~0.5
|
| 92 |
+
|
| 93 |
+
basic formula:
|
| 94 |
+
|
| 95 |
+
KanPiroMix + XSMix + ChikMix
|
| 96 |
+
|
| 97 |
+
关注我的TG频道看更多例图：https://t.me/majic_NSFW<br><br>
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
|
| 101 |
+
|
| 102 |
+
|
| 103 |
+
|
| 104 |
+
|
| 105 |
+
|
| 106 |
+
|