i

README.md

@@ -4,13 +4,14 @@
 
 Style2paints V4 is the current best AI driven lineart colorization tool.
 
-Different from presious end-to-end image-to-image translation methods, style2paints V4 is the **first** system to colorize a lineart **in real-life human workflow**, and the outputs are **layered**.
+Different from previous end-to-end image-to-image translation methods, style2paints V4 is the **first** system to colorize a lineart **in real-life human workflow**, and the outputs are **layered**.
 
 Inputs:
 
     ● Linearts
     ● (with or without) Human hints
     ● (with or without) Color style reference images
+    ● (with or without) Light location and color
 
 Outputs:
 
@@ -22,15 +23,15 @@ Outputs:
     ● Automatic rendering (separated layer)
     ● Automatic rendered colorization
 
-Style2paints V4 gives you results of the current highest quality. You are able to get separated layers from our system. These layers can be directly used in your painting workflow. Different from all previous AI driven colorization tools, our results are not 'JPG/PNG' images, and in fact, our results are 'PSD' layers.
+Style2paints V4 gives you results of the current highest quality. You are able to get separated layers from our system. These layers can be directly used in your painting workflow. Different from all previous AI driven colorization tools, our results are not single 'JPG/PNG' images, and in fact, our results are 'PSD' layers.
 
 Online APP: [http://s2p.moe/](http://s2p.moe/)
 
 User Instruction: [https://style2paints.github.io/](https://style2paints.github.io/)
 
 And we also have an official [Twitter](https://twitter.com/IlIIlIIIllIllII) account.
 
-# Help human via obeying their standard workflow!
+# Help human in their standard coloring workflow!
 
 Most human artists are familiar with this workflow:
 
@@ -39,29 +40,111 @@ Most human artists are familiar with this workflow:
 And the corresponding layers are:
 
     lineart layers + flat color layers + gradient layers + shading layers
-
-Our AI is also working in this way. Here we are showing some examples. For each figure, the left-top is input sketch, the right-top is the flat color, the left-bottom is the color gradient, and the last one is the shaded result.
 
-Here is the video: https://youtu.be/B6WEky9nY7Q
+Style2paints V4 is designed for this standard coloring workflow! In style2paints V4, you can automatically get separated results from each step!
+
+# Examples
+
+![logo](https://github.com/lllyasviel/style2paints/raw/master/temps/show/pip.jpg)
+
+Here we present some results in this ABCD format. Users only need to upload their sketch, select a style, and put a light source. 
+
+When the result is achieved immediately without any human color correction, we regard this result as **fully automatic result**. When the result needs some color correction, human can easily put some color hints on the canvas to guide the AI coloring process. In this case, we regard these results as **semi-automatic results**. If a result is semi-automatic, but the quantity of human color hint points is smaller than 10, we regard these results as **almost automatic result**. In this section, about half of the presented results are **fully automatic result**, and the others are all **almost automatic result**. Do notice that all the below results can be achieved with less than 15 clicks!
+
+**Here we provide a video to show how all below results are achieved.**
+
+The video is a pure screen record without any after modification or speed modification. 
+
+Here is the video: [https://youtu.be/B6WEky9nY7Q](https://youtu.be/B6WEky9nY7Q)
+
+*(Because this page is prepared before the video is recoreded, some numbers may have minor differences.)*
+
+## Example #1
+
+See video at: 11:28
+
+All human color modification: only 3 clicks.
 
 ![logo](https://github.com/lllyasviel/style2paints/raw/master/temps/show/8.jpg)
 
+*\*CC-BY-NC-SA-4.0 (c) Various artist of style2paints team, 2018. This image is OK for ACM/IEEE fair use.*
+
+## Example #2
+
+See video at: 06:19
+
+All human color modification: only 2 clicks.
+
 ![logo](https://github.com/lllyasviel/style2paints/raw/master/temps/show/5.jpg)
 
+*\*CC-BY-NC-SA-4.0 (c) Various artist of style2paints team, 2018. This image is OK for ACM/IEEE fair use.*
+
+## Example #3
+
+See video at: 01:40
+
+All human color modification: only 6 clicks.
+
 ![logo](https://github.com/lllyasviel/style2paints/raw/master/temps/show/2.jpg)
 
+*\*CC-BY-NC-SA-4.0 (c) Various artist of style2paints team, 2018. This image is OK for ACM/IEEE fair use.*
+
+## Example #4
+
+See video at: 00:42
+
+All human color modification: NO human color modification.
+
 ![logo](https://github.com/lllyasviel/style2paints/raw/master/temps/show/1.jpg)
 
+*\*CC-BY-NC-SA-4.0 (c) Various artist of style2paints team, 2018. This image is OK for ACM/IEEE fair use.*
+
+## Example #5
+
+See video at: 02:57
+
+All human color modification: NO human color modification.
+
 ![logo](https://github.com/lllyasviel/style2paints/raw/master/temps/show/3.jpg)
 
+*\*CC-BY-NC-SA-4.0 (c) Various artist of style2paints team, 2018. This image is OK for ACM/IEEE fair use.*
+
+## Example #6
+
+See video at: 07:57
+
+All human color modification: 11 clicks.
+
 ![logo](https://github.com/lllyasviel/style2paints/raw/master/temps/show/6.jpg)
 
+## Example #7
+
+See video at: 13:00
+
+All human color modification: only 6 clicks.
+
 ![logo](https://github.com/lllyasviel/style2paints/raw/master/temps/show/9.jpg)
 
+*\*CC-BY-NC-4.0 (c) Henjo. Only for this presentation.*
+
+## Example #8
+
+See video at: 04:27
+
+All human color modification: only 3 clicks.
+
 ![logo](https://github.com/lllyasviel/style2paints/raw/master/temps/show/4.jpg)
 
+## Example #9
+
+See video at: 09:46
+
+All human color modification: only 5 clicks.
+
 ![logo](https://github.com/lllyasviel/style2paints/raw/master/temps/show/7.jpg)
 
+*\*CC-BY-NC-SA-4.0 (c) Various artist of style2paints team, 2018. This image is OK for ACM/IEEE fair use.*
+
 # Know more about us!
 
 Online APP: [http://s2p.moe/](http://s2p.moe/)