4 points | by rvba 11 hours ago ago
2 comments
You need to build out a baseline style using text-to-image and then always add those images as "style reference" images in future prompts e.g. "Create a four-panel comic of bla bla bla. Use the attached images strictly as stylistic references only".
That will help keep the model on track.
I've seen people doing this with GPT Image 2.
You need to build out a baseline style using text-to-image and then always add those images as "style reference" images in future prompts e.g. "Create a four-panel comic of bla bla bla. Use the attached images strictly as stylistic references only".
That will help keep the model on track.
I've seen people doing this with GPT Image 2.