Prompt Engineering
Introduction
Workflow
To get as close to the imagined concept and as efficiently as possible,the following workflow is proposed:
- Checkpoint selection: Each model is trained for specific output. Use the right one!
- Use prompt perfector to get to a good descriptive prompt
- Use img2txt (CLIP) to retrieve a prompt from an example image that can be used to get detailed prompts for specific features
- Use a fixed seed, in order to same results for the same prompt.
- Use relative low resolution, but at the desired aspect ratio.
- Iterate the prompt until the concept is mainly displayed.
- Finalize the details. Upscale image and set higher iterations. Fine-tune the prompt until all details are correct.
- Save image and save prompt & settings.
Prompt perfecters
Using ChatGPT to optimize the prompt is efficient, because it is not always clear how the AI will respond to a certain prompt. There are templates available to help kickstart the prompt perfectioning via ChatGPT.