Unverified60% confidenceFactTime unknown
New-generation models such as FLUX and Z-Image, due to architectural improvements, achieve optimal results with a CFG value of 1 or even lower, whereas traditional Stable Diffusion models typically use CFG values of 7–12.
2
Sources
60%
Confidence
Long-term
Relevance
6/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedStable Diffusion XL采用基础模型加精炼模型的两阶段级联架构，先生成低分辨率底图再补充细节纹理67% similarUnverifiedSupra2-IMG uses CFG 3.0 as the default display value, which is lower than the 7.0–9.0 commonly used by Stable Diffusion.67% similarUnverifiedLTX-2.5 改进后的蒸馏模型在大幅降低算力需求的同时保留了远多于以往的完整模型质量，可在消费级 GPU 上运行62% similarUnverifiedCFG=4–4.5 is the recommended starting range for many Flux and SD3 series models, while SDXL-type models commonly use 5–8.61% similarUnverifiedStable Diffusion is based on the Latent Diffusion architecture, enabling high-quality image generation to run on consumer-grade GPUs.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/39522API
curl https://kongchang.com/api/v1/knowledge/claims/39522MCP
get_claim(id=39522)