Verified65% confidenceFactTime unknown
CFG Scale (Classifier-Free Guidance scale) controls the degree to which the generated result adheres to the prompt.
3
Sources
65%
Confidence
Long-term
Relevance
6/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedCFG guidance strength typically seeks the best balance between 5 and 12; too low deviates from the prompt, while too high produces oversaturation or artifacts.72% similarUnverified负向提示词在Stable Diffusion等开源模型中通过Classifier-Free Guidance（CFG）机制实现，CFG Scale通常设置在7-12之间72% similarUnverifiedCFG is a parameter controlling the strength of alignment between the generated result and the prompt, usually taking values of 5-9; acceleration LoRAs require CFG=1 because the model has already internalized the guidance signal during distillation, and continuing to use a high CFG would break the step-compression mapping.69% similarUnverifiedClassifier-free guidance (CFG) runs both a conditional branch and an unconditional branch simultaneously, amplifying the conditional signal by subtracting the unconditional direction from the conditional direction, trading a doubling of inference cost for quality improvement.68% similarUnverifiedWhen CFG is 1, negative prompts have no effect; if negative prompts are needed, the CFG value can be slightly increased (e.g., to 1.5).67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/39694API
curl https://kongchang.com/api/v1/knowledge/claims/39694MCP
get_claim(id=39694)