| --- |
| 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. |
|
|
