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

🛈 IMPORTANT!!!

You will need to search for, download, and load the model nemotron-3-nano-omni 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 nemotron-3-nano-omni

- This model far exceeded my expectations, it is fast I got on average 45 tokens per second on my AMD Strix Halo RyzenAI Workstation, it generates short concise prompts, with minimal rambling. The generated prompts produces images with stunning aesthetics.

- I set the max tokens to 1500, this higher value is to accommodate the reasoning tokens.

- If the image looks flat, check the logs in LM Studio, the last log entry will contain a JSON path x.choices[0].message.content if the content field is empty that means the LLM ran out of reasoning tokens, this can be resolved by increasing max_tokens.