526christian
commited on
Commit
•
297647f
1
Parent(s):
308d847
Update README.md
Browse files
README.md
CHANGED
@@ -7,14 +7,16 @@ tags:
|
|
7 |
license: creativeml-openrail-m
|
8 |
inference: true
|
9 |
---
|
10 |
-
High saturation is less frequently an issue in this version at 7 CFG than the last. But if it happens again, it helps to pull back to 6.
|
11 |
|
12 |
`<neg-sketch-2>` negative embedding highly recommended for realism and 3D style images (among others). It can be found here: https://huggingface.co/JPPhoto/neg-sketch-2
|
13 |
|
14 |
When prompting for paintings, I suggest using "framed, borders, photo" as your negative prompt to get fullscreen images and cut out any weird 3D-like people.
|
15 |
|
16 |
-
When prompting for illustrations, I like to use "photo
|
17 |
|
18 |
When prompting for realism, I normally use a negative prompt of `<neg-sketch-2>` at 1.1 weight and "(anime, render, pixar, illustration, sketch)" at 1.2 weight.
|
19 |
|
|
|
|
|
20 |
[Example images hosted on Civitai](https://civitai.com/models/15022?modelVersionId=132011) were generated in InvokeAI's Nodes using latent upscaling from close to ~512x resolution up a few hundred pixels each side at 0.55-0.65 strength w/ DDIM. This was followed up with an ESRGAN model upscale, then converting the image to latents and using ControlNet Tile in a latent to latent stage at 0.2-0.4 strength w/ DDIM.
|
|
|
7 |
license: creativeml-openrail-m
|
8 |
inference: true
|
9 |
---
|
10 |
+
High saturation is much less frequently an issue in this version at 7 CFG than the last. But if it happens again, it helps to pull back to 6.
|
11 |
|
12 |
`<neg-sketch-2>` negative embedding highly recommended for realism and 3D style images (among others). It can be found here: https://huggingface.co/JPPhoto/neg-sketch-2
|
13 |
|
14 |
When prompting for paintings, I suggest using "framed, borders, photo" as your negative prompt to get fullscreen images and cut out any weird 3D-like people.
|
15 |
|
16 |
+
When prompting for illustrations, I like to use "photo" or "realistic" as my negative prompt.
|
17 |
|
18 |
When prompting for realism, I normally use a negative prompt of `<neg-sketch-2>` at 1.1 weight and "(anime, render, pixar, illustration, sketch)" at 1.2 weight.
|
19 |
|
20 |
+
[Garbage-bin concepts LoRA](https://civitai.com/models/95391?modelVersionId=101827) recommended for any intense silliness.
|
21 |
+
|
22 |
[Example images hosted on Civitai](https://civitai.com/models/15022?modelVersionId=132011) were generated in InvokeAI's Nodes using latent upscaling from close to ~512x resolution up a few hundred pixels each side at 0.55-0.65 strength w/ DDIM. This was followed up with an ESRGAN model upscale, then converting the image to latents and using ControlNet Tile in a latent to latent stage at 0.2-0.4 strength w/ DDIM.
|