Unverified50% confidenceFactExact time
In Midjourney, a negative prompt-like effect can be achieved through the "--no" parameter or by using expressions such as "avoid" and "without" in the prompt.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/21/2026
First Seen
Valid until: 11/19/2026
Sources
Related Claims
UnverifiedMidjourney supports fine-grained control through parameters such as weight syntax (e.g., ::2 for doubled weight), negative prompts, style reference (--sref), and chaos value (--chaos for controlling variation diversity).62% similarUnverified对大语言模型而言，「不要做X」的负向约束有时比「要做Y」的正向指令更有效，因为负样本相当于在概率空间中设置了禁区59% similarUnverifiedDe-alignment (abliteration/uncensoring) removes safety restrictions through fine-tuning techniques; common methods include continued training on refusal-free datasets and modifying the model's internal refusal direction vectors through representation engineering.56% similarUnverifiedSetting the threshold for semantic caching involves a trade-off: a threshold that is too high results in a low hit rate, while one that is too low may incorrectly map semantically different questions and cause response quality issues.56% similarUnverifiedNegative constraints narrow the probability space by explicitly excluding undesired outputs, are equally important as positive instructions, and can reduce deviations caused by the model's creative improvisation.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/784219API
curl https://kongchang.com/api/v1/knowledge/claims/784219MCP
get_claim(id=784219)