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 llama-3.2-3b-imagegen 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 llama-3.2-3b-imagegen

• This model has been fined tuned for SDXL and Flux cinematic prompt generation.

• This model is small only 3 billion parameters so expect it to be a little bit stupid when it comes to understanding instructions, but when it does understand it does a very good job.

• I set the max_tokens to 80 to prevent the model from looping and adding random cinematic aethetics towards the end of the enhanced positive prompt, if your input prompt is long and descriptive you may want to increase this value, the maximin max_tokens value supported for Flux 2 Klein is 512 tokens

• I changed the temperature to 0.5 you can experiment with values between 0.5 and 0.7