Update README.md

README.md

@@ -3,11 +3,11 @@ license: creativeml-openrail-m
 ---
 **civitai**:https://civitai.com/models/30294/dreamirror-mix (更多预览在civitai/More preview in civitai)
 
-**这是一个画风更偏向于2D的2.5D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）。**
+所有的预览图没有使用embedding,lora
 
 **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。**
 
-**你可以用它尝试任何东西！我会不定时补充预览图。如果你觉得这个模型不错,可以评价一下以及上传你的图片。**
+**你可以用它尝试任何东西！**
 
 **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。**
 
@@ -17,17 +17,21 @@ license: creativeml-openrail-m
 
 **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**。
+**用于画面质量的正面提示词(像 best quality)是不必要的,会减少画面的可能性,还会使画面趋于一种风格。**
+
+**将你原本用在正面质量提示词上的权重,用在负面质量提示词上,那是更好的选择。**
 
 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)
+我一般在效果不符合预期时使用clip2
+
+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
 
 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 style more 2D preference for 2.5D 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).**
+All preview images do not use embedding,lora
 
 **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.**
 
@@ -41,16 +45,31 @@ If the **face is not in focus** in the Image (same for non-frontal), the face ap
 
 **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**.
+**Positive prompt for image quality (like best quality) are unnecessary and reduce the possibilities of the picture, also make the picture tend to be in a style.**
+
+**It's better to Use the weight you would have used for positive quality prompt on negative quality 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**.
 
+I usually use clip2 when the results don't meet expectations
+
 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
+我使用这两个VAE/I use these two VAEs:
+https://huggingface.co/stabilityai/sd-vae-ft-mse-original
+https://civitai.com/models/22354/clearvae
+
+**V3**
+![image](https://raw.githubusercontent.com/Fre2C/DreaMirror/main/Preview/V3/1383662622.png)
+![image](https://raw.githubusercontent.com/Fre2C/DreaMirror/main/Preview/V3/1061413964.png)
+![image](https://raw.githubusercontent.com/Fre2C/DreaMirror/main/Preview/V3/250608473.png)
+![image](https://raw.githubusercontent.com/Fre2C/DreaMirror/main/Preview/V3/2322320228.png)
+![image](https://raw.githubusercontent.com/Fre2C/DreaMirror/main/Preview/V3/2034939505.png)
+![image](https://raw.githubusercontent.com/Fre2C/DreaMirror/main/Preview/V3/4022912954.png)
+
 
 **V2.2**
 ![image](https://raw.githubusercontent.com/Fre2C/DreaMirror/main/Preview/V2.2/599645006.png)