About this paper
PREEN predicts interpretable editor presets for color style transfer by learning from pseudo-presets generated by a style-transfer teacher and refining a CLIP-conditioned regressor with LoRA, enabling fast and adjustable results.
We present PREEN (Preset Regression via an Exemplar-based Editor Network), which casts color style transfer as regression onto the 29 parameters of a deterministic image editor. Given a content image and a style reference, PREEN predicts a preset, a vector of editor slider values that is interpretable and editor-consumable, not a raster image. The key obstacle is supervision, since an arbitrary real reference lacks a preset ground truth. We therefore supervise with a style-transfer teacher, whose target looks we invert into the editor's parameter space as pseudo-presets, then pretrain a CLIP-conditioned regressor and refine it with LoRA under an image-level CIELAB loss. On the…
color style transferpreset regressionexemplar-based editor networkCLIP-conditioned regressorLoRApseudo-presetsstyle-transfer teacherCIELAB losssingle forward passinference-time strength knob
- Upvotes
- 5
- Authors
- 1
- Published
- Oct 27, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
PREEN: Exemplar-Based Color Style Transfer with Smartphone Editor Presets was first seen on Hugging Face · Daily papers on Nov 10, 2026. Since then it has appeared in 2 checks on 1 different day. Its best position was #27 of 30, reached on Nov 10, 13:28 UTC. It dropped off the list after Nov 10, 13:28 UTC.