Text-to-Image

Update README.md (Fix)

#1
by qpqpqpqpqpqp - opened
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -10,13 +10,13 @@ pipeline_tag: text-to-image
10
  # Example images containing prompts and/or workflows for each model version are available on either CivitAI or in the folder labeled "Images" which are seperated by version
11
  # NSFW Example images are only available on CivitAI
12
 
13
- https://civitai.com/models/1143097/willys-noob-realism
14
 
15
  <img src="https://cdn-uploads.huggingface.co/production/uploads/6411f2531e42164b9f0facef/Eq0MPlI05qU5gAhZH7bgK.png" style="width:571px;height:1012px;"/> <sup>This image is only a thumbnail</sup>
16
 
17
- This model and its version(s) were merged for the sole purpose of finally having a decent out of the box consistent Realism model based on Noob. The "HD" and "V-Pred" versions are made for higher resolution raw gens and upscaling.
18
 
19
- !!! If you are having problems, noisy images, or prompt issues please scroll down to *"Common Problems"* !!!
20
 
21
 
22
 
@@ -144,7 +144,7 @@ Initial release version.
144
 
145
  # Recommended Settings:
146
 
147
- TL:DR Its very simple, just prompt however you usually would for noob, but add "realistic", and "photorealism" after your quality tags.
148
 
149
  I suggest using Euler A with Beta scheduler, or DPM++ 2m SDE with Karras scheduler (does not work with v-pred) at a CFG of 5-7 and steps of 20-50, but feel free to experiment. Not all schedulers and settings work for everyone.
150
 
@@ -163,7 +163,7 @@ And here is my suggested negative prompt:
163
 
164
  (Negative prompt is no longer needed for quality images)
165
 
166
- ```worst quality, low quality, normal quality, monochrome, bad anatomy, ugly, (illustration, cartoon, anime), flat color, outline, smooth skin, blurry,```
167
 
168
 
169
 
@@ -205,7 +205,7 @@ Nobody using A1111 has actually expressed any issues. If you are having issues w
205
  Here is a list of working Schedulers for **A1111**: https://civitai.com/posts/11757173
206
 
207
 
208
- Some people have also been experiencing small VAE artifacts while using Reforge. This is likely due to your VAE settings not being set correctly. This model uses the default sdxl.vae.safetensors sdxl VAE.
209
 
210
 
211
 
 
10
  # Example images containing prompts and/or workflows for each model version are available on either CivitAI or in the folder labeled "Images" which are seperated by version
11
  # NSFW Example images are only available on CivitAI
12
 
13
+ https://civit.ai/models/1143097
14
 
15
  <img src="https://cdn-uploads.huggingface.co/production/uploads/6411f2531e42164b9f0facef/Eq0MPlI05qU5gAhZH7bgK.png" style="width:571px;height:1012px;"/> <sup>This image is only a thumbnail</sup>
16
 
17
+ This model and its versions were merged for the sole purpose of finally having a decent out of the box consistent Realism model based on Noob. The "HD" and "V-Pred" versions are made for higher resolution raw gens and upscaling.
18
 
19
+ !!! If you have problems, noisy images, or prompt issues, please, scroll down to *"Common Problems"* !!!
20
 
21
 
22
 
 
144
 
145
  # Recommended Settings:
146
 
147
+ TL:DR Its very simple, just prompt however you usually would for Noob, but add "realistic", and "photorealism" after your quality tags.
148
 
149
  I suggest using Euler A with Beta scheduler, or DPM++ 2m SDE with Karras scheduler (does not work with v-pred) at a CFG of 5-7 and steps of 20-50, but feel free to experiment. Not all schedulers and settings work for everyone.
150
 
 
163
 
164
  (Negative prompt is no longer needed for quality images)
165
 
166
+ ```worst quality, low quality, normal quality, monochrome, bad anatomy, ugly, (illustration, cartoon, anime), flat color, outline, smooth skin, blurry```
167
 
168
 
169
 
 
205
  Here is a list of working Schedulers for **A1111**: https://civitai.com/posts/11757173
206
 
207
 
208
+ Some people have also been experiencing small VAE artifacts while using Reforge. This is likely due to your VAE settings not being set correctly. This model uses the default SDXL VAE.
209
 
210
 
211