Commit
·
e5022ef
1
Parent(s):
d2de499
update readme
Browse files- .vscode/settings.json +7 -0
- README.md +1 -1
.vscode/settings.json
CHANGED
|
@@ -2,10 +2,17 @@
|
|
| 2 |
"cSpell.words": [
|
| 3 |
"controlnet",
|
| 4 |
"creativeml",
|
|
|
|
|
|
|
|
|
|
| 5 |
"Eding",
|
|
|
|
|
|
|
|
|
|
| 6 |
"loras",
|
| 7 |
"openrail",
|
| 8 |
"safetensors",
|
|
|
|
| 9 |
"webui"
|
| 10 |
]
|
| 11 |
}
|
|
|
|
| 2 |
"cSpell.words": [
|
| 3 |
"controlnet",
|
| 4 |
"creativeml",
|
| 5 |
+
"downsample",
|
| 6 |
+
"downsampled",
|
| 7 |
+
"downsampler",
|
| 8 |
"Eding",
|
| 9 |
+
"getdata",
|
| 10 |
+
"getpixel",
|
| 11 |
+
"lanczos",
|
| 12 |
"loras",
|
| 13 |
"openrail",
|
| 14 |
"safetensors",
|
| 15 |
+
"upscaled",
|
| 16 |
"webui"
|
| 17 |
]
|
| 18 |
}
|
README.md
CHANGED
|
@@ -38,7 +38,7 @@ A: From my experience SD has a hard time creating genuine pixel art (even with d
|
|
| 38 |
|
| 39 |
Q: Should I use this model with a post-processor?
|
| 40 |
|
| 41 |
-
A: Yes, I still recommend you do post-processing to clean up the image. This model is not perfect and will still have artifacts. Note that none of the sample output images are post-processed; they are raw outputs from the model.
|
| 42 |
|
| 43 |
Q: Will there be a better trained model of this in the future?
|
| 44 |
|
|
|
|
| 38 |
|
| 39 |
Q: Should I use this model with a post-processor?
|
| 40 |
|
| 41 |
+
A: Yes, I still recommend you do post-processing to clean up the image. This model is not perfect and will still have artifacts. Note that none of the sample output images are post-processed; they are raw outputs from the model. Consider sampling the image based on the location of the control grid checker faces. I will provide a custom script specialized for this in the near future.
|
| 42 |
|
| 43 |
Q: Will there be a better trained model of this in the future?
|
| 44 |
|