OracleZoom Combines On-Policy Self-Distillation and Reference Constraints to Cut Hallucinations in Extreme Super-Resolution
Shubhashis Roy Dipta · hf · 2026-09-10
OracleZoom, released on Hugging Face, tackles recursive image super-resolution at extreme magnifications. The method combines trajectory-based training with cross-scale supervision and a latent prior, constrained by reference signals, to reduce hallucinations that typically appear at high zoom factors. Inspired by on-policy self-distillation, it aims for more faithful high-resolution outputs.
More from Multimodal
- Full Seedance 2.5 prompt recreates early-2000s DV home video realism — SimplyAnnisa · 2026-09-10
- How to build 40+ second continuous talking videos with LTX 2.5 in ComfyUI — Majestic-Regret-3030 · 2026-09-10
- Paid Fable 5 to make a short film — it rented a PC, wrote, generated and edited everything — kleffew94 · 2026-09-10
- Stunning Midjourney subway image made with --sref 3110898898 — gizakdag · 2026-09-10
- DeepSeek V4.1 Flash nears Opus-class quality in motion video tests — mesmerlord · 2026-09-10
- Viral 1980s photo AI trend: full prompt to turn selfies into analog-era shots — aitrendz_xyz · 2026-09-10