license: creativeml-openrail-m
civitai:https://civitai.com/models/30294/dreamirror-mix (更多预览在civitai/More preview in civitai)
这是一个混合模型，如果有需要改进和做得不对的地方请指出来（如果你能说出纠正的方法最好，因为我可能不是很清楚）。
这个模型的方向是尽可能忠于提示词,能生成更多的东西(人物是主要的,但不代表其他事物的效果不重要),舒服的光影。
从AOM3:https://huggingface.co/WarriorMama777/OrangeMixs 和Anything:https://civitai.com/models/9409/or-anything-v5 知道了很多模型和学习了很多混合方面的经验,十分感谢。
使用建议:
如果在脸部不是焦点的画面中(非正面也是同样),脸部出现崩坏的情况,以及想提升面部质量,可以使用Hires. fix获得更好的面部,使用其他随机种或者工具也是不错的办法。(我认为这是混合了3D或者2.5D模型导致的,并没有什么很好的办法解决,如果你有办法在模型层面改善请告诉我。)
较高的分辨率(比512 * 512高一点)再加上Hires. fix,图片质量会更好(如果显存不够你可以尝试低倍率的Hires. fix或者其他放大方法)。
过高的,用于画面质量(像best quality这些)的正面和负面提示词是不必要的,会减少细节,也可能使画面趋于一种风格,以及无法对提示词做出反应。
如果觉得画面内容不够丰富,你可以尝试细致地描述,使画面更加贴近你的想象。
如果想要更强的明暗对比效果,可以尝试光影类lora,比如epi_noiseoffset: https://civitai.com/models/13941/epinoiseoffset (我曾在V1加入过它,但是它似乎会影响手指生成,所以去掉了,你可以自己使用它)
如果你想要更多的亚洲面孔,人物类lora是很好的选择,比如Doll Likeness系列:https://huggingface.co/Kanbara/doll-likeness-series
This is a merge model, so please point out if there is something that needs to be improved and done wrong (If you can say how to correct the best, because I may not be very clear).
The direction of this model is to be as faithful as possible to the prompt words, to be able to generate more things (the character is the main, but does not mean that the effect of other things is not important), comfortable light and shadow.
I know a lot of models and learn a lot of mixing experience from AOM3:https://huggingface.co/WarriorMama777/OrangeMixs and Anything:https://civitai.com/models/9409/or-anything-v5, thank you very much
Suggestions for use:
If the face is not in focus in the Image (same for non-frontal), the face appears to be falling apart, and you want to improve the quality of the face,you can use Hires. fix to get a better face, or use other seed or tools is also a good way.(I think this is because of the merge of 3D or 2.5D models,There is no good way to fix it,If you have a way to improve it at the model level please let me know.)
Higher resolution (a little higher than 512 * 512) plus Hires. fix, picture quality will be better (if the gpu memory is not enough you can try a Low magnification of Hires. fix or other upscale tools)
Overly high, positive and negative prompt for image quality (like best quality) are unnecessary and will reduce detail, and may tend to make the image look a specific style and the inability to respond to the prompt.
If you feel that the content of the picture is not rich enough, You can try to describe in detail to make the picture more closely to your imagination.
If you want a stronger contrast between light and dark, you can try light and shadow lora, such as epi_noiseoffset: https://civitai.com/models/13941/epinoiseoffset (I had added it in V1, but it seems to affect the finger generation, so remove it, you can use it yourself)
If you want more Asian faces, the Character class lora is a good choice, such as the Doll Likeness series: https://huggingface.co/Kanbara/doll-likeness-series
我使用这个VAE/I use this VAE:https://huggingface.co/stabilityai/sd-vae-ft-mse-original
V2
使用的模型/Use Models
chilloutmix_NiPrunedFp32Fix【fc2511737】
braBeautifulRealistic_v40【9c03252bea】
neverendingDreamNED【64b14b6ca5】
dpepmkmp【2180a29445】
CounterfeitV25【a074b8864e】
kawaiimixNijiV5Cute_v10【58f37f4736】
AnythingV5V3_v5PrtRE【7f96a1a9ca】
包含了chilloutmix,请务必遵守相关规约
Chilloutmix is included, please be sure to follow the relevant regulations
https://huggingface.co/dreamlike-art/dreamlike-diffusion-1.0/blob/main/LICENSE.md
配方/Recipe
use:https://github.com/hako-mikan/sd-webui-supermerger/
(chilloutmix_NiPrunedFp32Fix x (1-alpha) + braBeautifulRealistic_v40 x alpha)x(1-beta)+ neverendingDreamNED_bakedVae x beta alpha:0.5,0.75,0.85,0.85,0.75,0.75,0.75,0.75,0.85,0.75,0.85,0.85,0.85,0.5,0.6,0.75,0.75,0.35,0.35,0.35,0.5,0.5,0.35,0.35,0.8,0.8 beta:0.5,0.35,0.35,0.35,0.5,0.25,0.25,0.25,0.15,0.25,0.2,0.2,0.2,0.7,0.35,0.35,0.35,0.75,0.65,0.85,0.3,0.25,0.25,0.25,0.0,0.0
Naming step1 3d
(dpepmkmp x (1-alpha) + CounterfeitV25_25 x alpha)x(1-beta)+ kawaiimixNijiV5Cute_v10 x beta alpha:0.5,0.85,0.65,0.5,0.85,0.85,0.75,0.55,0.35,0.75,0.35,0.35,0.35,0.7,0.85,0.75,0.75,0.6,0.6,0.65,0.35,0.35,0.5,0.5,0.35,0.35 beta:0.5,0.35,0.35,0.35,0.5,0.25,0.25,0.25,0.15,0.25,0.2,0.2,0.2,0.7,0.35,0.35,0.35,0.75,0.65,0.85,0.3,0.25,0.25,0.25,0.0,0.0
Naming step1 2d
(step1 2D x (1-alpha) + AnythingV5V3_v5PrtRE x alpha)x(1-beta)+ step1 3D x beta alpha:0.5,0.7,0.35,0.6,0.7,0.6,0.6,0.6,0.25,0.35,0.35,0.35,0.35,0.65,0.35,0.35,0.35,0.75,0.25,0.25,0.75,0.75,0.75,0.75,0.35,0.35 beta:0.6,0.75,0.25,0.6,0.75,0.65,0.65,0.45,0.25,0.45,0.3,0.3,0.3,0.6,0.35,0.65,0.65,0.5,0.35,0.35,0.55,0.55,0.7,0.7,0.35,0.35
prune and get final version
V1
使用的模型/Use Models
basil mix【bbf07e3a1c】
chilloutmix_NiPrunedFp32Fix【fc2511737】
gape60-fp16【893cca5903】
NovelAI animefull-final-pruned【22fa233c2d】
anything-v3-full【abcaf14e5a】
CounterfeitV25_25【a074b8864e】
添加了epi_noiseoffset的lora/add this lora https://civitai.com/models/13941/epinoiseoffset
包含了chilloutmix,请务必遵守相关规约
Chilloutmix is included, please be sure to follow the relevant regulations
https://huggingface.co/dreamlike-art/dreamlike-diffusion-1.0/blob/main/LICENSE.md
配方/Recipe
use:https://github.com/hako-mikan/sd-webui-supermerger/
(basil mix x (1-alpha) + chilloutmix_NiPrunedFp32Fix x alpha)x(1-beta)+ gape60-fp16 x beta alpha:0.4,0.3,0.6,0.4,0.6,0.5,0.5,0.5,0.5,0.5,0.4,0.4,0.4,0.4,0.6,0.6,0.6,0.4,0.7,0.4,0.3,0.25,0.35,0.5,0.25,0.25 beta:0.35,0.2,0.35,0.1,0.1,0.2,0.3,0.3,0.35,0.35,0.0,0.0,0.0,0.4,0.2,0.1,0.1,0.6,0.6,0.25,0.2,0.1,0.2,0.2,0.0,0.0
Naming step1 3d
(NovelAI animefull-final-pruned x (1-alpha) + anything-v3-full x alpha)x(1-beta)+ gape60-fp16 x beta alpha:0.4,0.3,0.6,0.4,0.6,0.5,0.5,0.5,0.5,0.5,0.4,0.4,0.4,0.4,0.6,0.6,0.6,0.4,0.7,0.4,0.3,0.25,0.35,0.5,0.25,0.25 beta:0.35,0.2,0.35,0.1,0.1,0.2,0.3,0.3,0.35,0.35,0.0,0.0,0.0,0.4,0.2,0.1,0.1,0.6,0.6,0.25,0.2,0.1,0.2,0.2,0.0,0.0
Naming step1 2d
(step1 2d x (1-alpha) + CounterfeitV25_25 x alpha)x(1-beta)+ step1 3d x beta alpha:0.4,0.3,0.3,0.6,0.3,0.6,0.7,0.7,0.8,0.7,0.3,0.3,0.3,0.4,0.5,0.5,0.5,0.2,0.25,0.25,0.15,0.15,0.1,0.1,0.1,0.1 beta:0.5,0.75,0.8,0.3,0.75,0.7,0.1,0.1,0.1,0.1,0.2,0.2,0.2,0.4,0.2,0.1,0.1,0.8,0.25,0.25,0.4,0.4,0.5,0.5,0.0,0.0
add epiNoiseoffset:1
prune and get final version