Found a serious bug in packing "CLIP Text Encode" node into group.
- Dominant language
- Python
- Stars
- 133k
- Forks
- 15.7k
- Avg merge
- 1d 6h
- Merged PRs (30d)
- 155
Description
When packing multiple "CLIP Text Encode" nodes into a node group, if one of the text widgets is converted to input, it will cause CLIP to get confused. If you pack a Reroute node into a node group at the same time, you may even find that the connection is missing when you dissolve the node group.
When the prompts are slightly more complex, this can lead to completely unpredictable results.
Contributor guide
Assessment
This issue has not been assessed yet.