---
license: openrail++
tags:
- text-to-image
- stable-diffusion-xl
- sdxl
- realvisxl
- lightning
- gguf
- stable-diffusion-cpp
- tokforge
base_model:
- SG161222/RealVisXL_V4.0_Lightning
pipeline_tag: text-to-image
---

## TokForge

- **Website:** https://tokforge.ai
- **Discord:** https://discord.gg/Acv3CBtfVm
- **Google Play:** https://play.google.com/store/apps/details?id=dev.tokforge
- **iOS TestFlight:** https://testflight.apple.com/join/jnufjzRr

Runs on-device in the TokForge app.

# TokForge — RealVisXL V4.0 Lightning GGUF (SDXL Quality)

A single self-contained **GGUF** for [`stable-diffusion.cpp`](https://github.com/leejet/stable-diffusion.cpp),
packaging **[RealVisXL V4.0 Lightning](https://huggingface.co/SG161222/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.

This is the **GPU "Quality" image tier** for the [TokForge](https://tokforge.ai) Android app:
native **1024px photoreal** SDXL on **certified high-memory Qualcomm/Adreno** devices via the
OpenCL F16-GEMM route. It is **not** a CPU default — SDXL is too heavy for phone CPU — it is the
opt-in photoreal step-up above the DreamShaper fast route.

## Files

| 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 |

## Recommended render settings (SDXL Lightning, few-step)

```
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 tier
```

### stable-diffusion.cpp CLI example

```bash
sd -M img_gen \
  -m realvisxl-v40-lightning-q8_0.gguf \
  -p "close-up portrait, natural skin texture, 85mm, RAW photo, photorealistic" \
  --sampling-method dpm++2m --steps 6 --cfg-scale 1.5 \
  -W 1024 -H 1024 -o out.png
```

## Provenance & how this was built

1. Loaded `SG161222/RealVisXL_V4.0_Lightning` (SDXL diffusers, fp16). Lightning is a baked
   few-step distilled checkpoint (no LoRA to fuse).
2. Exported to a single original-format SDXL `.safetensors`.
3. Converted to GGUF with `stable-diffusion.cpp` (`-M convert --type q8_0`,
   keeping the VAE at f16 via `--tensor-type-rules '^first_stage_model\.=f16'`).

## License & attribution

- **License:** **openrail++** (inherited from RealVisXL V4.0 Lightning / SDXL).
- **Base model:** RealVisXL V4.0 Lightning by **SG161222** —
  https://huggingface.co/SG161222/RealVisXL_V4.0_Lightning
- Built on top of Stable Diffusion XL (Stability AI).

The original openrail++ terms and attribution requirements propagate to this GGUF and any
images generated with it.