Almanac
paper

FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining

paperactiveprovisionalfreestyle-free-control-of-style-content-dual-reference-generation-from-community-lora-mining-1a677bd7·1 events·first seen 2d ago

Aliases: FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining

Co-occurring entities

More like this (12)

Recent events (1)

4arXiv · cs.AI·2d ago·source ↗

FreeStyle: Dual-Reference Image Generation via Community LoRA Mining with Leakage Suppression

FreeStyle is a new framework for style-content dual-reference image generation that mines community LoRA models as compositional anchors to construct large-scale training triplets. The approach uses a two-stage curriculum with attention-level enrichment constraints and frequency-aware RoPE modulation to suppress semantic leakage between style and content references. The authors also introduce a benchmark with novel metrics including a style-invariant Content Alignment Score and a VLM-based Rejection Score for evaluating leakage suppression.