8,844
edits
Media creation with artificial intelligence: Difference between revisions
Media creation with artificial intelligence (view source)
Revision as of 23:02, 26 March 2026
, Thursday at 23:02no edit summary
Paradox-01 (talk | contribs) mNo edit summary |
Paradox-01 (talk | contribs) mNo edit summary |
||
| Line 88: | Line 88: | ||
=====ChatGPT===== | =====ChatGPT===== | ||
* '''Iterative prompting''': Describe the desired result as clearly as possible: Motive, perspective, colors, lights, shadows, art style. Refine the prompt step by step based on undesired aspects rather than expecting a perfect result on the first attempt. Negative prompts: You can also explicitly write what you don't want. | * '''Iterative prompting''': Describe the desired result as clearly as possible: Motive, perspective, colors, lights, shadows, art style. Refine the prompt step by step based on undesired aspects rather than expecting a perfect result on the first attempt. Negative prompts: You can also explicitly write what you don't want. | ||
** Caution: As for March 2026, you have explicitly tell ChateGPT to not crop the image in some scenarios. In that case you have to give it context like where the image should end and tell it how much "extra" space you want. Saying "don't crop the image" is to not specific enough. | |||
* '''Avoid quality loss''': If the GenAI degenerates the image quality because of too many iterations, try from a new start with combined text prompts. | * '''Avoid quality loss''': If the GenAI degenerates the image quality because of too many iterations, try from a new start with combined text prompts. | ||
* '''Reference images''': When supported, provide one or more images to guide style, composition, or subject consistency. This is often more reliable than text-only prompting. | * '''Reference images''': When supported, provide one or more images to guide style, composition, or subject consistency. This is often more reliable than text-only prompting. | ||