TokForge-DreamShaper-LCM-GGUF

Published by TokForge for on-device inference.

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

A single self-contained GGUF (f16) for stable-diffusion.cpp, packaging DreamShaper-7 (SD1.5, realistic finetune) with the LCM-LoRA fused into the UNet for fast, guidance-free few-step sampling.

This is the on-device fast image route for the TokForge 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

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

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 (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.

Credits

• DreamShaper 7 by Lykon (Civitai, Hugging Face). Used under the CreativeML OpenRAIL-M license and the creator's Civitai terms. Lykon's Civitai terms: no selling the model or merges of it.
• LCM-LoRA SD1.5 by Latent Consistency (Hugging Face). Used under the CreativeML OpenRAIL++-M license.
• Stable Diffusion v1.5 by Runway and CompVis (Hugging Face). Used under the CreativeML OpenRAIL-M license.
• Converted to GGUF with stable-diffusion.cpp by leejet (MIT).