Views
No views yet
stable-diffusion.cpp,
packaging RealVisXL V4.0 Lightning
(SDXL, photoreal, few-step Lightning). The UNet is q8_0, the VAE is kept at f16, both
CLIP text encoders included — everything in one file.| File | Size | Precision | Contents |
|---|---|---|---|
realvisxl-v40-lightning-q8_0.gguf | ~4.2 GB | q8_0 UNet / f16 VAE | CLIP-L + OpenCLIP-bigG + Lightning UNet + SDXL VAE |
sampler: dpm++2m
scheduler: discrete
steps: 6 (4 = fast floor, 8 = extra refinement)
cfg-scale: 1.5
resolution: 1024x1024 (SDXL native)
backend: OpenCL on high-memory Adreno (GPU); SDXL CPU is not a supported tier1sd -M img_gen \
2 -m realvisxl-v40-lightning-q8_0.gguf \
3 -p "close-up portrait, natural skin texture, 85mm, RAW photo, photorealistic" \
4 --sampling-method dpm++2m --steps 6 --cfg-scale 1.5 \
5 -W 1024 -H 1024 -o out.pngSG161222/RealVisXL_V4.0_Lightning (SDXL diffusers, fp16). Lightning is a baked
few-step distilled checkpoint (no LoRA to fuse)..safetensors.stable-diffusion.cpp (-M convert --type q8_0,
keeping the VAE at f16 via --tensor-type-rules '^first_stage_model\.=f16').