2
edits
Prompt engineering for image generation: Difference between revisions
Prompt engineering for image generation (view source)
Revision as of 22:08, 27 May 2023
, 27 May 2023→Stable Diffusion
No edit summary |
Soartificial (talk | contribs) Tags: Reverted Visual edit |
||
| Line 73: | Line 73: | ||
*'''Prompt weighting:''' varies between 1 and -1. Decimals can be used to reduce a prompt’s influence. | *'''Prompt weighting:''' varies between 1 and -1. Decimals can be used to reduce a prompt’s influence. | ||
*'''Negative prompting:''' in DreamStudo negative prompts can be added by using | <negative prompt>: -1.0 (e.g. | disfigured, ugly:-1.0, too many fingers:-1.0). <ref name="”16”"></ref> | *'''Negative prompting:''' in DreamStudo negative prompts can be added by using | <negative prompt>: -1.0 (e.g. | disfigured, ugly:-1.0, too many fingers:-1.0). <ref name="”16”"></ref> | ||
If you would like examples of how to create your own characters with stable diffusion you can find a guide [https://soartificial.com/create-your-own-characters-with-stable-diffusion/ here] | |||
===Jasper Art=== | ===Jasper Art=== | ||
| Line 104: | Line 105: | ||
The guidelines provided suggest: | The guidelines provided suggest: | ||
*Focusing on keywords during prompt engineering rather than rephrasings, as rephrasing does not have a significant impact on the quality of the generation. | * Focusing on keywords during prompt engineering rather than rephrasings, as rephrasing does not have a significant impact on the quality of the generation. | ||
*Trying multiple generations to collect a representative idea of what prompts may return. | *Trying multiple generations to collect a representative idea of what prompts may return. | ||
*To speed up the iteration process, the user should choose lower lengths of optimization, as the number of iterations and length of optimization do not significantly impact user satisfaction with the generation. | *To speed up the iteration process, the user should choose lower lengths of optimization, as the number of iterations and length of optimization do not significantly impact user satisfaction with the generation. | ||