---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
- dreamshaper
- lcm
- gguf
- stable-diffusion-cpp
- tokforge
- quantized
- q4_0
base_model:
- Lykon/dreamshaper-7
- latent-consistency/lcm-lora-sdv1-5
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 — DreamShaper-7 + LCM GGUF (Q4_0)

A **Q4_0-quantized** single self-contained **GGUF** 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 **6 GB-tier fast image route** for the [TokForge](https://tokforge.ai) apps — the
smaller sibling of [`TokForge-DreamShaper-LCM-GGUF`](https://huggingface.co/darkmaniac7/TokForge-DreamShaper-LCM-GGUF)
(f16, ~2.1 GB). It renders the same coherent people and hands (no SD-Turbo body-horror) at the
same few-step LCM speed class, but at a smaller download + RAM footprint so it fits the 6 GB
device tier where the f16 build is gated out.

## Files

| File | Size | Precision | Contents |
|------|------|-----------|----------|
| `dreamshaper-7-lcm-q4_0.gguf` | ~1.63 GB | Q4_0 (mixed) | CLIP text encoder (**F16**) + LCM-fused UNet (Q4_0 linears/1×1 convs, F16 3×3 convs) + VAE |

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

### Precision details (CLIP-safe quantization)

This GGUF was quantized with **stable-diffusion.cpp's own `-M convert --type q4_0`**, whose
`tensor_should_be_converted` rule **protects embeddings and norms** — it keeps every tensor whose
name contains `embedding` (and all `.bias` / `.scale` / norm tensors) at **F16**. So the CLIP
text encoder's `token_embedding.weight` stays **F16**.

This is deliberate and required: a *block-quantized* CLIP token-embedding (the failure mode of
some external blanket-quantizers) produces empty CLIP conditioning through `ggml_get_rows` and
makes sd.cpp abort at `conditioner.hpp GGML_ASSERT(!chunk_hidden_states.empty())`. Keeping CLIP
at F16 avoids that entirely.

Note the file is ~1.63 GB rather than ~0.6 GB because SD-1.5's UNet is dominated by **3×3
convolution weights** (`ne[0] = 3`), which are not divisible by Q4_0's block size of 32 and so
are kept at F16 by ggml (the same reason the working `gpustack` Q4_0 SD-1.5 GGUF is ~1.75 GB).
The Q4_0 win comes from the attention/projection linears and 1×1 convs. Verified type histogram:
690 F16 tensors + 440 Q4_0 tensors; CLIP `token_embedding.weight` = **F16**.

## 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-q4_0.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. Started from [`TokForge-DreamShaper-LCM-GGUF`](https://huggingface.co/darkmaniac7/TokForge-DreamShaper-LCM-GGUF)
   `dreamshaper-7-lcm-f16.gguf` (DreamShaper-7 with LCM-LoRA fused into the UNet, exported to a
   single SD1.5 GGUF, f16).
2. Quantized to Q4_0 with `stable-diffusion.cpp` (`leejet`):
   `sd -M convert -m dreamshaper-7-lcm-f16.gguf -o dreamshaper-7-lcm-q4_0.gguf --type q4_0`.
   sd.cpp's quantizer keeps CLIP / embeddings / norms at F16 (`model_loader.cpp
   tensor_should_be_converted`).
3. Verified the CLIP `token_embedding.weight` is **F16** in the output header, and ran a
   6-step LCM smoke render that produced a coherent on-prompt image.

## 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
- **Quantization tooling:** [stable-diffusion.cpp](https://github.com/leejet/stable-diffusion.cpp) by **leejet**
- 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.