darkmaniac7/TokForge-SD15-QNN-NPU

TokForge — SD1.5 (Qualcomm Hexagon NPU)

Stable Diffusion 1.5 image generation for the Qualcomm Hexagon NPU (HTP), packaged for on-device image generation in the TokForge Android app (dev.tokforge).

The model is quantized to W8A16 (8-bit weights, 16-bit activations) and compiled to QNN HTP context binaries, which run image generation directly on the phone's Hexagon DSP.

Based on

stable-diffusion-v1-5/stable-diffusion-v1-5.

Format

These are per-architecture QNN HTP context binaries, one set per Hexagon arch (V73, V75, V79, V81). They are not a portable format like GGUF — each binary is compiled for a specific Hexagon generation. The app reads the device's Hexagon arch and selects the matching set.

Binaries are forward-compatible: a set built for a lower Hexagon arch also runs on a higher-arch DSP, while native-arch sets are preferred for best performance.

File (per arch dir)	Role
unet.bin	UNet HTP context binary
vae_decoder.bin	VAE decoder HTP context binary
text_encoder.bin	CLIP text-encoder QNN binary
time_mlp.bin	host time-embedding weights
tokenizer.json, config.json	tokenizer + pipeline config

See manifest.json for the authoritative per-arch file set (with per-file size + md5) that the app uses to download the correct binaries for the device.

Usage

This bundle is loaded automatically by the TokForge Android app — it is not a standalone diffusers checkpoint. The app resolves the device Hexagon arch from manifest.json, downloads the matching binaries, and runs them on the device NPU.

License & attribution

Released under CreativeML OpenRAIL-M, matching its base model.

This model is a derivative of stable-diffusion-v1-5/stable-diffusion-v1-5. Please retain this attribution and observe the CreativeML OpenRAIL-M use restrictions.