Local Dream

32 downloads

Uploaded by: Psychopath
Version: 2.2.1 (build 52)

Local Dream versions

2.2.1 (build 52)
32 downloads
Size: 53.3 MiB
Publish Date: 2025-11-07
Category: Tools
Package: io.github.xororz.localdream
Minimum OS: Android 9.0
SHA1: 9074ce00b25e7ba11a7e7a0dac45bcb0edcea14a
Description: Run Stable Diffusion on Android Devices with Snapdragon NPU Acceleration. Also supports CPU/GPU inference. Quick Start 1. Download: Get the APK file 2. Install: Install the APK on your Android device 3. Select Models: Open the app and download the model(s) you want to use Features - 🎨 txt2img – Generate images from text descriptions - 🖼️ img2img – Transform existing images - 🎭 inpaint – Redraw selected areas of images - Prompt Weights – Emphasize certain words in prompts using syntax like (masterpiece:1.5). Same format as Automatic1111: https://github.com/AUTOMATIC1111/stable-diffusion-webui - Embeddings – Support for custom embeddings like EasyNegative. SafeTensor format is required. Convert .pt files to safetensors using: https://chino.icu/local-dream/pt2sf.py - Upscalers – 4x upscaling with realesrgan_x4plus_anime_6b and 4x-UltraSharpV2_Lite Technical Implementation NPU Acceleration - SDK: Qualcomm QNN SDK leveraging Hexagon NPU - Quantization: W8A16 static quantization for optimal performance - Resolution: Fixed 512×512 model shape - Performance: Extremely fast inference speed CPU/GPU Inference - Framework: Powered by MNN framework - Quantization: W8 dynamic quantization - Resolution: Flexible sizes (128×128, 256×256, 384×384, 512×512) - Performance: Moderate speed with high compatibility NPU High-Resolution Support After downloading a 512 resolution model, you can download patches to enable 768×768 and 1024×1024 image generation ⛔ Important Please note that quantized high-resolution models may produce images with poor layout. We recommend first generating at 512 resolution (optionally upscaling it to 2048), then using the high-resolution model for img2img (essentially Highres.fix). The suggested img2img denoise_strength is around 0.8. This workflow produces images with better layout and details. Device Compatibility NPU Acceleration Support Compatible with devices featuring: - Snapdragon 8 Gen 1 - Snapdragon 8+ Gen 1 - Snapdragon 8 Gen 2 - Snapdragon 8 Gen 3 - Snapdragon 8 Elite - Snapdragon 8 Elite Gen 5 - Non-flagship chips with Hexagon V68 or higher (e.g., Snapdragon 7 Gen 1, 8s Gen 3) ⚠️ Note: Devices outside this list cannot download NPU models. CPU/GPU Support - RAM Requirement: Approximately 2 GB of available memory - Compatibility: Most Android devices from recent years

Download (53.3 MiB)