README.md

---
title: ASASR Super-Resolution
emoji: 🎨
colorFrom: indigo
colorTo: purple
sdk: gradio
sdk_version: 6.10.0
app_file: app.py
short_description: Faithful x4 image super-resolution with FLUX.1-dev dual-LoRA
startup_duration_timeout: 1h
license: cc-by-nc-4.0
---

<div align="center">

# ✦ ASASR · Coloring the Noise

**Adversarial Sobolev Alignment for Faithful Image Super-Resolution**
*ICML 2026*

Hongbo Wang · Huaibo Huang · Pin Wang · Jinhua Hao · Chao Zhou · Ran He

[![Paper](https://img.shields.io/badge/Paper-arXiv-4338ca?style=for-the-badge)](https://arxiv.org/abs/2605.23264)
[![Code](https://img.shields.io/badge/Code-GitHub-181722?style=for-the-badge)](https://github.com/wafer-bob/ASASR)
[![Model](https://img.shields.io/badge/Model-Hugging%20Face-ff9d00?style=for-the-badge)](https://huggingface.co/wafer-bob/ASASR)
[![License](https://img.shields.io/badge/License-CC--BY--NC--4.0-6f42c1?style=for-the-badge)](https://creativecommons.org/licenses/by-nc/4.0/)

</div>

---

## Overview

This Space is an interactive demo for **Coloring the Noise: Adversarial
Sobolev Alignment for Faithful Image Super-Resolution** (ICML 2026).

ASASR performs **x4 image super-resolution** with a **FLUX.1-dev** backbone and
**dual-LoRA inference**:

- `sr_lora/pytorch_lora_weights_v2.safetensors` — base SR LoRA.
- `dpo_lora/adapter_model.safetensors` — ASASR AS-DPO alignment LoRA.

Both LoRAs are loaded from
[**wafer-bob/ASASR**](https://huggingface.co/wafer-bob/ASASR). The base model is
[**black-forest-labs/FLUX.1-dev**](https://huggingface.co/black-forest-labs/FLUX.1-dev),
which is **gated** and requires an `HF_TOKEN` Space secret with model access.

## How to use

1. **Upload** a low-resolution square image (≈128 × 128), or click one of the
   bundled examples.
2. Click **✦ Super-Resolve** to run the 28-step ASASR sampler on ZeroGPU.
3. **Drag the ImageSlider** to compare the low-resolution input against
   the 512 × 512 ASASR reconstruction.

The interface is centered on an interactive before/after comparison slider, with
a clean hero header, six standard Gradio examples, and a collapsible citation
block. A modern light theme with an indigo/violet accent is used throughout.

## Demo UI

- **Hero header** with the ICML 2026 badge, paper title, author list, and
  quick-link buttons to the paper, code, and model.
- **Centerpiece** `gradio_imageslider` comparison view (Input LR | ASASR HR).
- **Standard Gradio examples** — six diverse 128 × 128 crops wired to the
  super-resolution function with lazy example caching.
- **Footer** with a CC-BY-NC-4.0 license notice and a collapsible BibTeX
  citation block.

## Setup notes

- The Space runs on **ZeroGPU**; the inference function is decorated with
  `@spaces.GPU` with a tunable duration (`ASASR_GPU_DURATION`, default 45 s,
  clamped to 30–300 s).
- Asset resolution is deferred to the first request unless a valid `HF_TOKEN`
  secret is present, in which case a startup prefetch warms the cache.
- Model artifacts are cached under `/tmp/.cache/huggingface` to stay within the
  ephemeral disk budget.

## License

ASASR code and weights are licensed under
[**CC-BY-NC-4.0**](https://creativecommons.org/licenses/by-nc/4.0/) for
non-commercial research use only. The demo also depends on the non-commercial
terms of FLUX.1-dev.

## Citation

<details>
<summary>BibTeX</summary>

```bibtex
@inproceedings{wang2026asasr,
  title     = {Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super-Resolution},
  author    = {Wang, Hongbo and Huang, Huaibo and Wang, Pin and Hao, Jinhua and Zhou, Chao and He, Ran},
  booktitle = {International Conference on Machine Learning (ICML)},
  year      = {2026}
}
```

</details>

## References

- **ASASR model weights:** <https://huggingface.co/wafer-bob/ASASR>
- **ASASR source code:** <https://github.com/wafer-bob/ASASR>
- **Paper (arXiv):** <https://arxiv.org/abs/2605.23264>
- **FLUX.1-dev base model:** <https://huggingface.co/black-forest-labs/FLUX.1-dev>