alosha-painter / README.md
YesWhyNot's picture
Upload folder using huggingface_hub
404ee20 verified
|
Raw History Blame Contribute Delete
2.42 kB
---
license: mit
tags:
- pytorch
- onnx
- flow-matching
- generative-art
- face-generation
pipeline_tag: image-to-image
---
# Alosha Painter
**Alosha Painter** is a generative computer vision model designed to draw and generate human faces using a custom **Flow Matching UNet** (`FlowMatchingUNet`). The model was trained on synthetic facial datasets collected by scraping [ThisPersonDoesNotExist.com](https://thispersondoesnotexist.com).
This repository contains the full model definition, training scripts, PyTorch EMA checkpoints, optimized ONNX exports (FP32, FP16, and INT8), and a local FastAPI demo server for quick image generation testing.
---
## Repository Structure
```text
.
β”œβ”€β”€ run.py # FastAPI demo server (PyTorch runtime)
β”œβ”€β”€ run_onnx.py # FastAPI demo server (ONNX Runtime)
β”œβ”€β”€ scrape.py # Data collection script for ThisPersonDoesNotExist
β”œβ”€β”€ train.py # FlowMatchingUNet architecture & training pipeline
β”œβ”€β”€ data/
β”‚ └── faces/ # Scraped training dataset
└── weights/
β”œβ”€β”€ checkpoint_latest.pth # PyTorch EMA model checkpoint
β”œβ”€β”€ unface.onnx # Standard FP32 ONNX export
β”œβ”€β”€ unface_fp16.onnx # FP16 precision ONNX model (GPU)
└── unface_int8.onnx # Quantized INT8 ONNX model (CPU)
```
---
## Running the Demo Server
A lightweight FastAPI server is provided in `run.py` and `run_onnx.py` as a demo to test generation outputs via HTTP GET requests.
### 1. PyTorch Runtime Demo
```bash
python run.py
```
### 2. ONNX Runtime Demo
```bash
python run_onnx.py
```
Once running, access `http://localhost:8000/` in a web browser or run:
```bash
curl http://localhost:8000/ --output generated_face.png
```
Each request runs the flow-matching ODE sampler (`steps=20`), applies 2x bicubic upsampling, and returns a PNG image.
---
## Technical Details
* **Architecture:** Custom Flow Matching UNet (`FlowMatchingUNet`)
* **Sampling:** ODE vector-field integration
* **Checkpointing:** Exponential Moving Average (EMA) weights (`ckpt["ema"]`)
* **ONNX Exports:** Pre-compiled FP32, FP16, and INT8 quantized binaries for fast CPU/GPU deployment without PyTorch overhead.
---
## Dataset & Training
1. **Scrape Training Dataset:**
```bash
python scrape.py
```
2. **Train Model:**
```bash
python train.py
```