license: other
license_name: stabilityai-ai-community
license_link: https://huggingface.co/stabilityai/sdxl-turbo/blob/main/LICENSE.md
tags:
- stable-diffusion-xl
- sdxl-turbo
- qualcomm
- hexagon
- qnn
- npu
- text-to-image
- tokforge
library_name: qnn
pipeline_tag: text-to-image
inference: false
TokForge — SDXL-Turbo (Qualcomm Hexagon NPU)
SDXL-Turbo image generation for the Qualcomm Hexagon NPU (HTP), packaged for on-device
image generation in the TokForge Android app (dev.tokforge). This is the higher-quality
1024×1024 tier alongside the SD1.5 NPU bundle.
The model is quantized to W8A16 (8-bit weights, 16-bit activations) and compiled to QNN HTP context binaries that run on the phone's Hexagon DSP. The pipeline uses fp16 text encoders and a TAESDXL tiny-VAE decoder, and is guidance-free (few-step distilled, one UNet pass per step).
Based on
Format
QNN HTP context binaries (W8A16), native 1024px (128×128 latent). These are compiled for the Hexagon DSP and are not a portable format like GGUF. The shipping set is V75-native and is forward-compatible (a lower-arch binary also runs on a higher-arch DSP), covering Hexagon V73 → V81.
| Stage | File |
|---|---|
| CLIP-L text encoder (fp16) | text_encoder_1_fp16.bin |
| OpenCLIP-bigG text encoder (fp16) | text_encoder_2_fp16.bin |
| combined embedding MLP | sdxl_emb_mlp.bin |
| UNet | unet.bin |
| VAE decode (TAESDXL tiny-VAE) | taesdxl_decoder.mnn |
| tokenizers | tokenizer/, tokenizer_2/ |
See manifest.json for the authoritative file set (with per-file size + md5) that the app uses to
download the bundle.
Usage
This bundle is loaded automatically by the TokForge Android app — it is not a standalone diffusers
checkpoint. The app downloads the file set from manifest.json and runs the binaries on the device NPU.
License & attribution
This model is a derivative of stabilityai/sdxl-turbo
and is distributed under the Stability AI Community License
(LICENSE). Attribution to Stability AI
and retention of the license text are required.