The source images for this workflow is attached as a zip file.

This workflow requires my Comfyui-lmstudio-prompt-enhancer custom node which is installable via Comfy Manager.

Learn more about this custom node

🛈 IMPORTANT!!!

You will need to search for, download, and load the model mistral-large-instruct-2411 in LM studio. You will also need to start the API server and generate an API Key. Learn how to configure LM Studio here.

Notes for using mistral-large-instruct-2411

• This workflow and model are extremely large and resource-intensive. On Windows 11 with my Strix Halo AMD Ryzen AI Max+ 395 CPU and Radeon 8060S GPU (128 GB unified memory), I achieved only ~1 token/second, and the processes consumed most of my system's resources while doing so.

• If the workflow appears to hang on the LM Studio Prompt Enhancer node, don’t worry this is expected.

• I set max tokens to 520, the max token length for Flux 2 prompts is 512, you can lower it if you don't want the LLM to ramble.