Independent publisher

Todd Tanner

LostBeard

Hardware-agnostic edge ML, client-side neural network inference/training, and cross-backend GPU compute. I focus on running large models natively in the browser and on desktop via C# transpilation; bypassing ONNX Runtime and heavy JS wrappers in favor of raw WebGPU, WebGL, CUDA, and WebAssembly kernels. Author of: SpawnDev.ILGPU.ML

Models in Library1

Datasets in Library0

Models on Hugging Face1

Followers1

Compare the published evidence

This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.

Reported licenses: mit. Open a record to review its specific license and conditions.

Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.

Models

Model

spawnscene-models

Todd Tanner

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

Open weights mit

View model