Scaling ChatGPT to Gemini Image Workflow

Hello WebNutch community, I'm working on a workflow that generates targeted images using ChatGPT and Gemini, and I'm looking for ways to optimize it. My current process involves using ChatGPT to create detailed prompts, then Gemini to generate images based on those prompts. I manually refine the output in Photoshop to ensure consistency and quality. However, steps 1 and 2 are time-consuming because I'm doing them one by one. I'd like to automate these steps while maintaining output quality. Ideally, I'm looking for a solution that can handle batch processing or streamline the prompt-to-image pipeline. If you have suggestions for simple automation methods, tools, or workflows that could help, I'd appreciate it. The WebNutch marketplace has a wide range of automation workflows and AI prompts, so I'm hoping someone in the community has experience with a similar setup. I currently have ChatGPT Plus and Gemini Pro subscriptions, so solutions that integrate with these tools would be great. Any guidance, video tutorials, or real-world examples would be helpful. Let's discuss ways to optimize this workflow and make it more efficient.