Unverified50% confidenceFactExact time
Classifier-Free Guidance (CFG) is one of the most mainstream guidance techniques in diffusion models and flow matching models, discarding conditions with a certain probability during training and, during sampling, subtracting the unconditional prediction from the conditional one via a formula and amplifying the guidance strength.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedClassifier-free guidance (CFG) originally came from diffusion generative models; the approach is to compute both conditional and unconditional predictions during sampling, then use a weight w to amplify the difference between them, with the formula ε = ε_uncond + w·(ε_cond − ε_uncond).77% similarUnverifiedCFG is a core hyperparameter in diffusion models, rooted in a 2022 research finding, and works by enhancing responsiveness to text descriptions through a weighted mixture of the predictions from the conditional and unconditional denoising paths.76% similarUnverified文本引导的去噪过程本质上是Classifier-Free Guidance（CFG）机制在起作用，模型同时预测有条件和无条件的噪声估计，两者差值被放大后引导生成方向73% similarUnverifiedCFG performs conditional and unconditional predictions separately during inference and interpolates and amplifies them via the formula output = uncond + guidance_scale × (cond - uncond), at the cost of requiring two forward passes per step.69% similarUnverifiedFSDP shards model parameters, gradients, and optimizer states across multiple GPUs, and is the mainstream solution for training models with hundreds of billions of parameters67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1046695API
curl https://kongchang.com/api/v1/knowledge/claims/1046695MCP
get_claim(id=1046695)