DeOldify

This version of DeOldify has been converted to run on the Axera NPU using w8a16 quantization.

This model has been optimized with the following LoRA:

Compatible with Pulsar2 version: 5.0-patch1

Convert tools links:

For those who are interested in model conversion, you can try to export axmodel through

• The repo of AXera Platform, which you can get the detail of guide

• Pulsar2 Link, How to Convert ONNX to axmodel

Support Platform

• AX650
  • M4N-Dock(爱芯派Pro)
  • M.2 Accelerator card

Chips	model	cost
AX650	colorize_stable	377 ms

How to use

Download all files from this repository to the device

root@ax650:~/deoldify# tree
.
|-- model
|   `-- colorize_stable.axmodel
|-- python
|`-- run_axmodel.py
|`-- requirements.txt

Inference

Input Data:

|-- image
|   `-- 1850Geography.jpg

Inference with M.2 Accelerator card

$cd python
$python3 gradio_demo.py
[INFO] Available providers:  ['AXCLRTExecutionProvider']
[INFO] Using provider: AXCLRTExecutionProvider
[INFO] SOC Name: AX650N
[INFO] VNPU type: VNPUType.DISABLED
[INFO] Compiler version: 5.0-patch1 2295293f
[INFO] Using provider: AXCLRTExecutionProvider
[INFO] SOC Name: AX650N
[INFO] VNPU type: VNPUType.DISABLED
[INFO] Compiler version: 5.0-patch1 2295293f

==================================================
🌐 AI图片上色 Web UI 已启动！
🔗 本地访问: http://127.0.0.1:7860
🔗 局域网访问: http://10.126.33.124:7860
==================================================

Then open the link in the browser to use the web UI:

Inference with AX650 Host, such as M4N-Dock(爱芯派Pro)

root@ax650 ~/realesrgan #python3 run_axmodel.py --input_path image/1850Geography.jpg --model_path colorize_stable.axmodel
[INFO] Available providers:  ['AxEngineExecutionProvider']
[INFO] Using provider: AxEngineExecutionProvider
[INFO] Chip type: ChipType.MC50
[INFO] VNPU type: VNPUType.DISABLED
[INFO] Engine version: 2.12.0s
[INFO] Model type: 2 (triple core)
[INFO] Compiler version: 5.0-patch1 2295293f
Color image save to `./sr_colorized.jpg`

Output: