Unverified50% confidenceFactExact time
Classifier-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.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedCFG=1 means no interpolation amplification is applied at all, causing the generation process to degrade into pure unconditional diffusion, rendering the prompt ineffective as a guide.78% similarUnverified在扩散模型中，较高的CFG（Classifier-Free Guidance）值会让输出更贴近提示词但更保守，较低的值给模型更多自由发挥空间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71% similarUnverifiedClassifier-free guidance (CFG) uses unconditional predictions as the weak signal, whereas autoguidance uses a weak model as the weak signal.70% similarVerifiedCFG Scale (Classifier-Free Guidance scale) controls the degree to which the generated result adheres to the prompt.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1002373API
curl https://kongchang.com/api/v1/knowledge/claims/1002373MCP
get_claim(id=1002373)