Research model for low-light image enhancement with continuous, controllable brightness, built on Flux 2 Klein.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
ControlLight is a research model for low-light image enhancement from the Shenzhen Institutes of Advanced Technology (Chinese Academy of Sciences) and Zhejiang University. The paper is titled "ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement" (arXiv 2605.25569, 2026).
It brightens dark images generatively while letting the user set the target light level along a linear control scale, aiming to preserve image detail and consistency. According to a YouTube creator summary, it is built on Flux 2 Klein, and the code, training code and dataset have been released. The project page describes Light100K, a continuous low-light enhancement dataset built to give fine-grained supervision for controllable enhancement.
It is aimed at researchers and practitioners working on image restoration and editing. The project page provided no license, hosted demo or pricing details, and the repository and weight links were not in the supplied material.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Image editing tool for brightening dark images with exact control over light level, using generative brightening that preserves detail. Built on Flux 2 Klein; code, training code and dataset released.
Closest neighbours by meaning, not just by category.
Model · Black Forest Labs
9B-parameter open-weights image generation and editing model from Black Forest Labs, built for low-latency use.
Model · Black Forest Labs
5.6B-parameter open-weights model from Black Forest Labs for image editing, text-to-image and multi-reference composition.
Model
Feed-forward single-image relighting model with physically based light control, using intrinsic conditioning from a coarse 3D scene.
Model · Black Forest Labs
Black Forest Labs image model with bounding-box layout control, reference-image input and native 4K output.
Model
Research model for video relighting that jointly generates relit video and per-frame environment maps, no camera poses needed.
Research · Google
Research method for free-view rendering and relighting of full-body dynamic humans from four sparse RGB views.
