Unverified50% confidenceFactExact time
Classifier-Free Guidance (CFG) was proposed by Jonathan Ho and Tim Salimans in 2022, with typical CFG scale values ranging from 7 to 15.
1
Sources
50%
Confidence
Long-term
Relevance
8/8/2026
First Seen
Sources
Related Claims
Unverified大多数模型的默认CFG值在7-12之间，对于材质表现丰富的场景，适中的CFG值（7-9）通常能在忠实度与自然感之间取得最佳平衡61% similarUnverifiedCFG的数学公式为ε_guided = ε_uncond + w × (ε_cond - ε_uncond)，典型CFG值范围是5-1556% similarUnverifiedGLM 4.6's performance on code evaluation benchmarks such as HumanEval, MBPP, and SWE-bench, as well as comprehensive capability benchmarks such as MMLU and GPQA, is on par with Claude 3.4 and Claude 3.4.5.51% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/711266API
curl https://kongchang.com/api/v1/knowledge/claims/711266MCP
get_claim(id=711266)