search

IuvenisSapiens / ComfyUI_Qwen2-VL-Instruct

The successful integration of Qwen2-VL-Instruct into the ComfyUI platform has enabled a smooth operation, supporting (but not limited to) text-based queries, video queries, single-image queries, and multi-image queries for generating captions or responses.
Apache License 2.0
66 stars 8 forks source link

Can't use the output from this in a normal ComfyUI workflow #12

Open thoughtfission opened 2 months ago

thoughtfission commented 2 months ago

I can't use the output from this in a normal ComfyUI workflow. How do I integrate this into CUI workflows? The text output seems to be a strange format. I've tried using intermediate nodes to convert the format but that doesn't help. I really want to use this, it seems extremely powerful based on my limited testing.

gt732 commented 2 months ago

Same issue, the output is not a text string that can be connected to other nodes

thoughtfission commented 2 months ago

I re-wrote the nodes.py script. Now works in my workflows.

gt732 commented 2 months ago

I re-wrote the nodes.py script. Now works in my workflows.

same