Przemysław Mejna commited on
Commit
0f85623
1 Parent(s): 3dc3e54

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +73 -0
README.md CHANGED
@@ -1,3 +1,76 @@
1
  ---
2
  license: openrail
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: openrail
3
  ---
4
+
5
+ # Conceptart embedding version 1.0
6
+
7
+ This model is made for Stable Diffusion 2.0 `checkpoint 768`
8
+
9
+ ### Introduction
10
+
11
+ The
12
+
13
+ ### For whom is this model?
14
+
15
+ This model is targeted toward people who would love to create a more artistic stuff in SD,
16
+ to get a cool logo, or stickers concepts, or baseline for an amazing poster. For sure as well
17
+ for concept artists needing inspiration or indie game dev - who might need some assets.
18
+ This embedding will be useful as well for all fans of bording games/table top rpg-s.
19
+
20
+ ### How to use it?
21
+
22
+ Simply drop the conceptart-x file (where `x` is a number of training steps) into the folder named `embeddings`. It should appear in your
23
+ SD instance main folder. In your prompt just type in: "XYZ something in style of `conceptart-x`". This is just an example. The most important part is the `conceptart-x`.
24
+
25
+ I would recommend you to first try each of them as they all might behave a bit different.
26
+
27
+ ### Issues
28
+
29
+ Currently, the model has some issues. It tends to have grayish/dull colors sometimes. The object's elements are not ideally coherent.
30
+ The improvements will come with future versions. You might expect them in the following weeks.
31
+
32
+ ### The strengths
33
+
34
+ One of the biggest strengths of this model is pure creativity and out of the box with proper prompting a good quality of output.
35
+ The strongest part of the model is a good quality improvement with img2img.
36
+
37
+ I think ofthen the usual workflow will look as following (ideas):
38
+
39
+ 1. You prompt-craft and create cool designs,
40
+ 2. You select ones you like (sometimes smaller objects/elements/designs from the output)
41
+ 3. You go to img2img to get more variations, or you select a smaller element that you like and you generate a bigger version of it. Then
42
+ you improve on the new one up until you are satisfied.
43
+ 4. You use another embedding to get a surprisingly amazing output! Or you already have a design you like!
44
+ 5. At The same time you might like to keep the design and upscale it to get a great resolution.
45
+
46
+ ### Examples
47
+
48
+ ***Basketballs*** with japanese dragons on them: [Imgur](https://imgur.com/73gQCXb)
49
+
50
+ I have used the one of the outputs, selected the object I liked with the rectangle took in img2img authomatic1111 ui, and went throught two img 2 img iterations to get the output.
51
+
52
+ Prompt:
53
+ `((basketball ball covered in colourful tattoo of a dragons and underground punk stickers)), illustration in style of conceptart-200, oil painting style
54
+ Negative prompt: bad anatomy, unrealistic, abstract, random, amateur photography, blurred, underwater shot, watermark, logo, demon eyes, plastic skin, ((text))
55
+ Steps: 30, Sampler: Euler a, CFG scale: 11.5, Seed: 719571754, Size: 832x832, Model hash: 2c02b20a, Denoising strength: 0.91, Mask blur: 4`
56
+
57
+ ***Anime demons***
58
+
59
+ Just one extra refinement in img2img. [Imgur](https://imgur.com/KBt2mWB)
60
+
61
+ Prompt:
62
+ `colored illustration of dark beast pokemon in style of conceptart-200, [bright colors]
63
+ Negative prompt: bad anatomy, unrealistic, abstract, cartoon, random, amateur photography, blurred, underwater shot, watermark, logo, demon eyes, plastic skin, ((text)), ((multiple characters)) ((desaturated colors))
64
+ Steps: 24, Sampler: DDIM, CFG scale: 11.5, Seed: 1001839889, Size: 704x896, Model hash: 2c02b20a`
65
+
66
+ ***Cave entrance***
67
+
68
+ Straight out comparison between the different embeedings. At the end result with vanilla SD 2.0 768. [Imgur](https://imgur.com/6MtiGUs)
69
+
70
+ Prompt:
71
+ `colored illustration of dark cave entrance in style of conceptart-200, ((bright background)), ((bright colors))
72
+ Negative prompt: bad anatomy, unrealistic, abstract, cartoon, random, amateur photography, blurred, underwater shot, watermark, logo, demon eyes, plastic skin, ((text)), ((multiple characters)) ((desaturated colors))
73
+ Steps: 24, Sampler: DDIM, CFG scale: 8, Seed: 1479340448, Size: 768x768, Model hash: 2c02b20a`
74
+
75
+
76
+ Enjoy! Hope you will find it helpful!