The text encoder layer used to represent your prompt.
Typical 1-2Default 1
CLIP is the text encoder: it turns your prompt into numbers the image model reads. CLIP skip chooses how many layers before the end of the encoder that reading is taken from.A value of 1 reads the last layer; 2 reads the one before it. The prompt is understood differently, not simply more loosely.Support and useful values depend on the model. Many anime models are trained for 2. Follow the selected model's suggestion where it gives one.
The examples on this page were made from one prompt, one model and one seed, changing only the setting shown. Other pictures, models and settings respond differently; compare on your own request with the seed and the other settings fixed.