Downloads · 30 days
0
darkmaniac7/TokForge-SD15-LCM-Style-Cartoon-b1
TokForge-SD15-LCM-Style-Cartoon-b1 is a text-to-image model from darkmaniac7. Use it when you need an image from a text prompt. The card lists the license as creativeml-openrail-m.
Published by TokForge for on-device inference.
Downloads · 30 days
0
Access
Public
Updated Oct 12, 2026
Repo size
1.2 GB
Likes
0
Public
Click a slice to open those files.
.weight1.1 GB · 93%
From the Hugging Face model README
Published by TokForge for on-device inference.
Runs on-device in the TokForge app.
Batch-1-capable MNN export of the Cartoon SD1.5-LCM styled bundle for the TokForge
Android app. The UNet is traced at batch-1 with dynamic spatial axes
(sample=[1,4,-1,-1]) so the app's CFG-skip engine runs a single conditional UNet
pass at cfg=1.0, one UNet pass per step instead of the legacy batch-2 build's two.
Versioned -b1 companion to the live repo. Requires the TokForge batch-1 CFG-skip
engine (app vc421+). Older app builds (vc412 and earlier) keep using the non--b1
repo. CLIP / VAE / tokenizer are byte-identical to the base; only unet.mnn(.weight)
differs.