This is a simple workflow I use to analyze images and videos and help create prompts.

I use Qwen3-VL-32B-Instruct-abliterated-v1-GGUF Q4 and Q5 VLM, but many VLM models are available.

There is a link for Qwen3-VL-32B-Instruct-abliterated-v1-GGUF models in the workflow. Any other model you will need to find for yourself.

Qwen3.5-Uncensored Advanced (GGUF) node REPLACES The former QwenVL Advanced nodes and you may have problems if you don't uninstall the old node package.

If you want instruction for any of the nodes I use, please look to the creator's documentation.

Feel free to message me and ask questions and I will do my best to help you when I am able.