README.md

---
license: mit
tags:
- inpainting
- onnx
---

# SpawnScene models

Models SpawnScene (https://spawnscene.com) runs on SpawnDev.ILGPU.ML in the browser, in a form that engine takes.

## migan_float.onnx

MI-GAN (Picsart AI Research, "MI-GAN: A Simple Baseline for Image Inpainting on Mobile Devices", ICCV 2023), the plain
512 network `migan.onnx` from https://huggingface.co/andraniksargsyan/migan, MIT licence (LICENSE-MI-GAN, unchanged).

Changed: float32 I/O instead of uint8 - inputs `image` [B,3,H,W] and `mask` [B,1,H,W] are FLOAT (values 0..255; mask
255 = known pixel, 0 = fill), the output `result` [B,3,H,W] is FLOAT 0..255, and the graph's four Cast(to=uint8) became
Cast(to=float). Weights untouched. Against the original on onnxruntime: max |difference| 1/255 (rounding).
Script: SpawnScene tools/migan_float_io.py.