A DreamShaper-7 + LCM SD1.5 MNN bundle (the TokForge SD15_LCM_MNN fast few-step image model) with the Storybook Illustration art-style LoRA fused into the UNet at export time. Renders a coherent 512px image in 4 steps on the in-process MNN diffusion engine — full MNN speed, the style baked in.

9-file MNN bundle: unet.mnn(.weight) (INT8, LCM + style fused), reference SD1.5 f16 text_encoder.mnn(.weight) + vae_decoder.mnn(.weight), vocab.json, merges.txt, alphas.txt.

Provenance & licenses

Website: <a href="https://tokforge.ai" target="_blank" rel="noopener noreferrer" class="text-blue-400 hover:text-blue-300 underline underline-offset-2 transition-colors">https://tokforge.ai
Discord: <a href="https://discord.gg/Acv3CBtfVm" target="_blank" rel="noopener noreferrer" class="text-blue-400 hover:text-blue-300 underline underline-offset-2 transition-colors">https://discord.gg/Acv3CBtfVm
Google Play: <a href="https://play.google.com/store/apps/details?id=dev.tokforge" target="_blank" rel="noopener noreferrer" class="text-blue-400 hover:text-blue-300 underline underline-offset-2 transition-colors">https://play.google.com/store/apps/details?id=dev.tokforge
iOS TestFlight: <a href="https://testflight.apple.com/join/jnufjzRr" target="_blank" rel="noopener noreferrer" class="text-blue-400 hover:text-blue-300 underline underline-offset-2 transition-colors">https://testflight.apple.com/join/jnufjzRr

Base: Lykon/dreamshaper-7 — CreativeML-OpenRAIL-M
LCM adapter: latent-consistency/lcm-lora-sdv1-5 — openrail++
Style LoRA: osmr/stable-diffusion-v1-5-lora-iv-ghibli — MIT

All components are permissively licensed (no Civitai-NC). Fused with diffusers.fuse_lora() (fp32 ΔW before INT8 quant); CLIP/VAE reused unchanged from the SD1.5 reference (the style LoRA is UNet-only).

darkmaniac7/TokForge-SD15-LCM-Style-Ghibli

TokForge

TokForge SD1.5-LCM Styled — Storybook Illustration

Provenance & licenses

darkmaniac7/
TokForge-SD15-LCM-Style-Ghibli