README.md

metadata

title: OracleZoom
emoji: 🔎
colorFrom: yellow
colorTo: gray
sdk: gradio
sdk_version: 5.50.0
python_version: 3.12.12
app_file: app.py
startup_duration_timeout: 45m
pinned: true
license: mit
short_description: Zoom any photo to 256x, one 4x step at a time
tags:
  - super-resolution
  - image-to-image
  - diffusion
  - zoom
models:
  - dipta007/OracleZoom
  - stabilityai/stable-diffusion-3-medium-diffusers
  - Qwen/Qwen2.5-VL-3B-Instruct
datasets:
  - dipta007/OracleZoom-4KLSDB-train

OracleZoom

Upload a photo, pick a point, and watch it zoom to 256x. Four steps of 4x, each one drawn from the last.

• Paper: https://arxiv.org/abs/2609.06490
• Code: https://github.com/dipta007/OracleZoom
• Project page: https://dipta007.github.io/OracleZoom/
• Model: https://huggingface.co/dipta007/OracleZoom

Running it yourself

The Space needs an HF_TOKEN secret. Stable Diffusion 3-medium is gated, so the token has to come from an account that has accepted its licence. Nothing in the code reads the token directly; huggingface_hub picks up HF_TOKEN on its own.

Hardware: ZeroGPU. The pipeline holds about 27 GB of weights, well inside the 48 GB that a large slice gives. ZeroGPU is Gradio-only, so a Docker Space cannot host this.

What is in here

app.py is the interface. zoom.py is the recursion, flattened from the research repo so it runs in memory with no disk round-trips and lets the zoom window sit off centre. video.py renders the clip. vendor/ holds four files copied from Chain-of-Zoom (MIT, see vendor/COZ-LICENSE), because Spaces do not support git submodules. The only edit to them pins weights_only=True on three torch.load calls, whose default flipped in torch 2.6.

Honest limits

Past the first step or two there is no ground truth left to recover, so the deep levels are plausible detail rather than measured detail. The zoom is a crop of your photo, not a real lens moving closer. The paper says which claims we do and do not make.