Update README.md
Browse files
README.md
CHANGED
@@ -3,8 +3,8 @@ license: openrail
|
|
3 |
---
|
4 |
<h1>ITRobo2022 model. Trained on SD 1.5.</h1>
|
5 |
|
6 |
-
I really like the Robo-Diffusion model (https://huggingface.co/nousr/robo-diffusion), but most of what you can get with it is robot heads. :)
|
7 |
-
In my model I tried to emphasize full-length images of robots. I also get good results on a homogeneous background, which makes it easier to cut out objects for further work
|
8 |
However, good results are also obtained with mixed queries. Try it. Good luck!
|
9 |
|
10 |
!!! Use this token at the beginning of the prompt: <b>itrobo2022</b><br><br>
|
@@ -16,8 +16,8 @@ Prompt: <i>ITRobo2022 (a full body photo of pug)+, isolated, high resolution pho
|
|
16 |
Negative prompt: <i>(duplicate)+++, deformed, no leg, blurry, no head, headless, watermarks, writings, text, marks, ugly, a lot of fingers, mutation, too many legs</i><br>
|
17 |

|
18 |
|
19 |
-
Best results on
|
20 |
-
DDIM
|
21 |
-
steps:20
|
22 |
-
CFG scale 7
|
23 |
512x512
|
|
|
3 |
---
|
4 |
<h1>ITRobo2022 model. Trained on SD 1.5.</h1>
|
5 |
|
6 |
+
I really like the Robo-Diffusion model (https://huggingface.co/nousr/robo-diffusion), but most of what you can get with it is robot heads. :)<br>
|
7 |
+
In my model I tried to emphasize full-length images of robots. I also get good results on a homogeneous background, which makes it easier to cut out objects for further work.<br>
|
8 |
However, good results are also obtained with mixed queries. Try it. Good luck!
|
9 |
|
10 |
!!! Use this token at the beginning of the prompt: <b>itrobo2022</b><br><br>
|
|
|
16 |
Negative prompt: <i>(duplicate)+++, deformed, no leg, blurry, no head, headless, watermarks, writings, text, marks, ugly, a lot of fingers, mutation, too many legs</i><br>
|
17 |

|
18 |
|
19 |
+
Best results on:<br>
|
20 |
+
DDIM<br>
|
21 |
+
steps:20<br>
|
22 |
+
CFG scale 7<br>
|
23 |
512x512
|