Core ML SDXL โ€” RealVisXL V5.0 (768, split_einsum, 6-bit)

Core ML conversion of SG161222/RealVisXL_V5.0 for on-device text-to-image on Apple Neural Engine (iOS / macOS), used by the Localmee app.

  • Converted with apple/ml-stable-diffusion torch2coreml
  • 768x768 native, SPLIT_EINSUM attention, 6-bit palettization, fp16-fix VAE
  • License: CreativeML OpenRAIL++-M (inherited from the base model)

All credit to the original authors. This is a format conversion only; weights are unchanged apart from 6-bit palettization.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for BulentOngun/coreml-realvisxl-v5

Finetuned
(5)
this model