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 ornith-1.0-35b 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 ornith-1.0-35b

• This model this model is fast I got on average 52 tokens per second on my AMD Strix Halo RyzenAI Workstation. -generates detailed prompts, with minimal rambling. The generated prompts produces images with expert composition and color grading.

• I set the max tokens to 3500, this higher value is to accommodate this model's deep reasoning.

• 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.

• this model tends to start the enhanced positive prompt's string with newline characters "\n" for now it does not appear to cause any problems.