Negative Prompt
Image & Video AIInstructions telling an AI image generator what NOT to include in the output — used to avoid common artifacts and unwanted elements.
A negative prompt is a feature in AI image generators (especially Stable Diffusion) that lets you specify what you don't want. While your main prompt describes the desired image, the negative prompt describes what to avoid.
Common negative prompts include: 'blurry, low quality, extra fingers, deformed hands, watermark, text, cropped' — addressing known weaknesses of AI image generation. Experienced users maintain standard negative prompt templates that dramatically improve output quality.
Not all image generators expose negative prompts to users. Midjourney handles much of this internally. DALL-E doesn't have explicit negative prompting. Stable Diffusion and its frontends (Fooocus, ComfyUI, AUTOMATIC1111) give full negative prompt control.
Real-World Example
In Stable Diffusion adding 'deformed hands, extra fingers, blurry, low quality' as a negative prompt dramatically improves output quality — telling the AI what mistakes to avoid.
Related Terms
More in Image & Video AI
FAQ
What is Negative Prompt?
Instructions telling an AI image generator what NOT to include in the output — used to avoid common artifacts and unwanted elements.
How is Negative Prompt used in practice?
In Stable Diffusion adding 'deformed hands, extra fingers, blurry, low quality' as a negative prompt dramatically improves output quality — telling the AI what mistakes to avoid.
What concepts are related to Negative Prompt?
Key related concepts include Stable Diffusion, Prompt, Diffusion Model, Checkpoint. Understanding these together gives a more complete picture of how Negative Prompt fits into the AI landscape.