---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
- dreamshaper
- lcm
- gguf
- stable-diffusion-cpp
- tokforge
base_model:
- Lykon/dreamshaper-7
- latent-consistency/lcm-lora-sdv1-5
pipeline_tag: text-to-image
---

# TokForge — DreamShaper-7 + LCM GGUF

A single self-contained **GGUF** (f16) for [`stable-diffusion.cpp`](https://github.com/leejet/stable-diffusion.cpp),
packaging **[DreamShaper-7](https://huggingface.co/Lykon/dreamshaper-7)** (SD1.5, realistic
finetune) with the **[LCM-LoRA](https://huggingface.co/latent-consistency/lcm-lora-sdv1-5)**
fused into the UNet for fast, guidance-free **few-step** sampling.

This is the on-device **fast image route** for the [TokForge](https://tokforge.ai) Android app —
the realistic, **non-cursed** replacement for base SD-Turbo on the CPU/OpenCL GGUF tier. It
renders coherent people and hands (no SD-Turbo body-horror) at the same size/speed class, and
uses the **same realistic base** TokForge ships on its MNN and NPU image tiers.

## Files

| File | Size | Precision | Contents |
|------|------|-----------|----------|
| `dreamshaper-7-lcm-f16.gguf` | ~2.1 GB | f16 | CLIP text encoder + LCM-fused UNet + VAE (single GGUF) |

`MD5SUMS` and `manifest.json` carry the integrity hash + render defaults.

## Recommended render settings (LCM, few-step, guidance-free)

```
sampler:      lcm
scheduler:    lcm
steps:        6   (4 = fast floor, 8 = extra refinement)
cfg-scale:    1.5
resolution:   512x512 (SD1.5 native; 256/384 presets also work)
```

### stable-diffusion.cpp CLI example

```bash
sd -M img_gen \
  -m dreamshaper-7-lcm-f16.gguf \
  -p "a busy outdoor street market crowded with people shopping, candid street photo" \
  --sampling-method lcm --scheduler lcm --steps 6 --cfg-scale 1.5 \
  -W 512 -H 512 -o out.png
```

## Provenance & how this was built

1. Loaded `Lykon/dreamshaper-7` (SD1.5 diffusers, fp16).
2. Fused `latent-consistency/lcm-lora-sdv1-5` into the UNet (`LCMScheduler`).
3. Exported the fused pipeline to a single original-format SD1.5 `.safetensors`.
4. Converted to GGUF f16 with `stable-diffusion.cpp` (`-M convert --type f16`).

## License & attribution

- **License:** [CreativeML OpenRAIL-M](https://huggingface.co/spaces/CompVis/stable-diffusion-license)
  (inherited from DreamShaper-7 / Stable Diffusion 1.5). Use is subject to the OpenRAIL-M use
  restrictions.
- **Base model:** DreamShaper-7 by **Lykon** — https://huggingface.co/Lykon/dreamshaper-7
- **Adapter:** LCM-LoRA SD1.5 by **Latent Consistency** —
  https://huggingface.co/latent-consistency/lcm-lora-sdv1-5
- Built on top of Stable Diffusion 1.5 (Runway/CompVis/Stability).

No additional restrictions are imposed by this repackaging; the original OpenRAIL-M terms and
attribution requirements propagate to this GGUF and any images generated with it.