SDXL 1.0 finetunes on vucinatim/spectrogram-captions for 89 epochs(800 steps). It generates spectrograms for simple sounds. It currently does not produce very good sound effects, but I will train the model for longer in the future.

Downloads last month
37
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Dataset used to train sr5434/SDXL-v1.0-sfx-step-800

Space using sr5434/SDXL-v1.0-sfx-step-800 1