RealVisXL V5.0 Lightning β€” GGUF (Off Grid build)

GGUF conversions of RealVisXL V5.0 Lightning for on-device image generation with stable-diffusion.cpp. Converted with sd.cpp's -M convert so the tensors are correctly named and load directly β€” the community GGUF quants of this model are mis-exported and fail get sd version from file.

sample

Files

  • realvisxl-v5.0-lightning-Q8_0.gguf β€” best quality
  • realvisxl-v5.0-lightning-Q4_K.gguf β€” lighter / lower RAM

Use with stable-diffusion.cpp

sd -M img_gen -m realvisxl-v5.0-lightning-Q8_0.gguf -p "your prompt" -o out.png \
  -W 1024 -H 1024 --steps 6 --cfg-scale 1.5 --sampling-method euler

Built for Off Grid AI Desktop β€” a private, fully on-device AI app (offgridmobileai.co).

Credit & license

Original model: https://huggingface.co/SG161222/RealVisXL_V5.0_Lightning β€” created by its respective authors. License: openrail++ (carried over from the original; its use restrictions apply). This is a format conversion (quantization) only; all credit for the model belongs to the original creators.

Downloads last month
88
GGUF
Model size
3B params
Architecture
Hardware compatibility
Log In to add your hardware

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for offgrid-ai/realvisxl-v5.0-lightning-GGUF

Quantized
(2)
this model