List your company

Soundscape-to-image generation on SoundingSVI 169K

16.839FIDSounDiT
11.5336447.3448283.156118.96718May 19, 2025

Evaluation results

MethodLinks
SounDiT2025.0516.83953.875.357.275.372.9
PixArt + MHCA2025.0534.10851.857.847.43974.3
GlueGen2025.0574.255056.64046.177.6
Sound2Scene2025.0578.13758.662.346.737.473.5
CoDiPre-trained=true2025.0587.02764.161.24030.280
AudioTokenBackbone/Base Model=SD12025.05105.47250.957.252.755.379.7
AudioTokenPre-trained=true2025.05142.4416051.924.818.488.4
AudioTokenBackbone/Base Model=SD22025.05149.47350.455.924.931.184.5