Text-to-Image
Diffusers
English
Not-For-All-Audiences
art
RedHotTensors commited on
Commit
4da1d50
1 Parent(s): d5aa050

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -50,6 +50,8 @@ Place the model checkpoint in the ``models/checkpoints`` folder. The optional Bo
50
  The model is zero-terminal-SNR with V-prediction. Use the ModelSamplingDiscrete node to configure it properly.
51
  <img style="margin-top: 0; width: 500px;" src="https://huggingface.co/RedRocket/Fluffyrock-Unbound/resolve/main/comfyui-1.webp">
52
 
 
 
53
  ## Quality Embeddings
54
 
55
  Experimental textual inversion embeddings in a similar vein to the [Boring Embeddings](https://huggingface.co/FoodDesert/Boring_Embeddings) are provided above.
 
50
  The model is zero-terminal-SNR with V-prediction. Use the ModelSamplingDiscrete node to configure it properly.
51
  <img style="margin-top: 0; width: 500px;" src="https://huggingface.co/RedRocket/Fluffyrock-Unbound/resolve/main/comfyui-1.webp">
52
 
53
+ If you are using a KarrasScheduler and zsnr, set sigma_max to 160. Do not use zsnr with the default KSampler karras schedule as the sigma_max will not be set correctly.
54
+
55
  ## Quality Embeddings
56
 
57
  Experimental textual inversion embeddings in a similar vein to the [Boring Embeddings](https://huggingface.co/FoodDesert/Boring_Embeddings) are provided above.