Implicit neural fields, sometimes encoded by a multilayer perceptron (MLP) that maps from coordinates (e.g., xyz) to indicators (e.g., signed distances), have proven exceptional promise as a high-fidelity and compact illustration. Nonetheless, the dearth of an everyday and express grid construction additionally makes it difficult to use generative modeling immediately on implicit neural fields as a way to synthesize new information. To this finish, we suggest HyperDiffusion, a novel method for unconditional generative modeling of implicit neural fields. HyperDiffusion operates immediately on MLP weights and generates new neural implicit fields encoded by synthesized MLP parameters. Particularly, a set of MLPs is first optimized to faithfully signify particular person information samples. Subsequently, a diffusion course of is educated on this MLP weight area to mannequin the underlying distribution of neural implicit fields. HyperDiffusion permits diffusion modeling over a implicit, compact, and but high-fidelity illustration of advanced indicators throughout 3D shapes and 4D mesh animations inside one single unified framework.