CelesteImperia
/

SDXL-QNN

Model card Files Files and versions

CelesteImperia: SDXL QNN (Snapdragon NPU Native)

The elite tier of optimization. This repository contains NPU-Native DLC files forged specifically for the Qualcomm Hexagon NPU (Snapdragon X Elite).

🐉 The Snapdragon Advantage

NPU-Native: Forged using the Qualcomm AI Stack (QNN/SNPE).
Slim King: 10.3GB master weights compressed to 2.39GB via Enhanced INT8 Quantization.
Hardware-Mapped: Fixed shapes (1024x1024) ensure maximum hardware block utilization.

📦 Components

unet/sdxl_unet_npu.dlc: The INT8 masterpiece.
tinyvae/: DLC-native VAE for hardware-accelerated previews.
clip/: NPU-optimized text encoders.

⚙️ Specifications

Target: Hexagon NPU
Input Geometry: Fixed 1x4x128x128 (Latent)
Quantization: Enhanced Per-Channel INT8

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for CelesteImperia/SDXL-QNN

Base model

stabilityai/stable-diffusion-xl-base-1.0

Quantized

(21)

this model