Hi,created this advanced captioniong workflow and system instructions to generate Captions for Flux for image batches. Since Flux uses two text encoders Clip L (77 tokens) and T5 (256 tokens) I implemented two caption streams. A NL pass for the T5 and a comma seq Pass for Clip L. With small datasets I tend to use both streams, this gives me the possibillity to either prompt with Natural language or asa comma seperated sequence. To run the GPT4O Component u need to add your OpenAI Api to your root folder. Will update this workflow soon again. Enjoy for now.

Files with SHA256: de3dc044a141eda7c6f7d61f261678b9a2090df021a3f398e1cb6bdd5d46711f