Write me a Stable Diffusion prompt for retro science fiction woman
- User
Write me a Stable Diffusion prompt for retro science fiction woman
- Assistant
prompt: A retro science fiction woman, slovenly, couch potato, A. Leslie Ross style. neg prompt: ((smiling)), (((duplicate))), ((mutilated)), ((couple)), (out of frame), extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), ((cloned face)), (((disfigured))). out of frame, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck)))
- User
Your prompt kinda worked, but a third leg or other distortions sometimes appear. Also, why did you include "slovenly" and "couch potato"? I tried without them, and at least it wasn't any worse. Also the A. Leslie Ross part didn't help much.
What do all these parentheses do? And why are there sometimes multiple?
- Assistant
I apologize for any confusion my previous response may have caused. If you're looking to create a visually striking and aesthetically pleasing image, you can tailor the generation of the Stable Diffusion model to your specific needs by utilizing positive and negative attributes. Positive prompts serve as keywords that highlight the features you want included in the image, while negative prompts exclude features you want to avoid. The parentheses function as a special operator that allows you to adjust the strength of a keyword, with each set of parentheses around a word increasing its strength by 0.1 from the default value of 1.0. Additionally, you can also specify the desired strength of a keyword by writing it as (keyword: strength). It's important to bear in mind, however, that the image generation process isn't infallible, and you may come across errors such as unwanted features or duplicates. Nevertheless, negative prompts can be helpful in mitigating these issues, although they don't provide an absolute guarantee. If you'd like, here's a new prompt you might want to experiment with:
Prompt: (masterpiece), a retro science fiction woman, ((retrofuturistic style)), (retro illustration), (best quality), (extreme high detailed), majestic, dramatic pose, tight suit, stunning, very beautiful, 80's movie, looking at you, stunning, sci-fi, action girl Negative Prompt: ((disfigured)), (((duplicate))), ((mutilated)), ((extra)), (white border), (out of frame), extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), ((cloned face)), extra legs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck))), (watermark), (monochrome)
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.
Identical first prompt
- Human-written demonstration (OpenAssistant volunteers)Compare side by side →
- Human-written demonstration (OpenAssistant volunteers)Compare side by side →
- Human-written demonstration (OpenAssistant volunteers)Compare side by side →
- Human-written demonstration (OpenAssistant volunteers)Compare side by side →
- Human-written demonstration (OpenAssistant volunteers)Compare side by side →
- Human-written demonstration (OpenAssistant volunteers)Compare side by side →