xebemacozydyqy/CLIP Text Encode And Enhance

Version 4 updates: Small code optimizations. Removed angle calculation between prompt vector and contextual vector due to high computational load and low efficiency. Contextual vector can be disabled by setting "mean". Added a second output designed to connect to the "negative" input and containing a vector midway between the prompt vector and the contextual vector. Version 3 updates: Note: now, when connecting something via clip, the CFG must be reduced by a factor of 2-2.5 for the connected thing to work properly. Fixed a bug when there are no delimiters in the prompt. Three new settings aff

<iframe src="https://silytics.si/embed/item/7ab4c9a2-1474-479b-b3d1-4c3411e0b009" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.