Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models Paper • 2605.21573 • Published 14 days ago • 107
thedeoxen/refcontrol-FLUX.2-klein-4B-reference-depth-lora Image-to-Image • Updated 6 days ago • 52 • 3
view article Article MONET: Lowering the bar for World-Class Image Generation research. jasperai • 6 days ago • 10
Ultra-High-Resolution Image Synthesis: Data, Method and Evaluation Paper • 2506.01331 • Published Jun 2, 2025 • 2
PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion Paper • 2605.23902 • Published 12 days ago • 45
SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers Paper • 2605.22668 • Published 13 days ago • 40 • 3
SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers Paper • 2605.22668 • Published 13 days ago • 40