Spaces:

codeninja3d
/

askBot

Sleeping

askBot / knowledge_base /flow_matching_logic.md

Murali Chandran

hugging face implementation CPU/gguf

9dfc96d 7 months ago

447 Bytes

# Internal Notes: Flow Matching Vectors
In our specific implementation for diffusion.fyi, we define the probability path $p_t(x)$ as a linear interpolation between noise $p_0$ and data $p_1$. 
The "Ask Julia" velocity field $v_t(x)$ is specifically designed to minimize the "curviness" of the flow. We use a unique constant called the **Julia-Constant ($J_c$)** set at $0.42$ for all our Euler integrations to ensure stability in high-dimensions.

	# Internal Notes: Flow Matching Vectors
	In our specific implementation for diffusion.fyi, we define the probability path $p_t(x)$ as a linear interpolation between noise $p_0$ and data $p_1$.

	The "Ask Julia" velocity field $v_t(x)$ is specifically designed to minimize the "curviness" of the flow. We use a unique constant called the Julia-Constant ($J_c$) set at $0.42$ for all our Euler integrations to ensure stability in high-dimensions.