SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices
Paper • 2601.08303 • Published • 21
Diffusion models
-
-
SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers
Paper • 2411.10510 • Published • 9 -
Dynamic Chunking Diffusion Transformer
Paper • 2603.06351 • Published • 16 -
Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion
Paper • 2603.06577 • Published • 50 -
DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing
Paper • 2603.28713 • Published • 23 -
MMFace-DiT: A Dual-Stream Diffusion Transformer for High-Fidelity Multimodal Face Generation
Paper • 2603.29029 • Published • 13 -
EditCrafter: Tuning-free High-Resolution Image Editing via Pretrained Diffusion Model
Paper • 2604.10268 • Published • 12 -
Rethinking Cross-Layer Information Routing in Diffusion Transformers
Paper • 2605.20708 • Published • 111 -
i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models
Paper • 2606.11289 • Published • 17 -
DataEvolver: Self-Evolving Multi-Agent Data Construction for Text-Rich Image Generation
Paper • 2606.31537 • Published • 27 -
CineMobile: On-Device Image-to-Video Diffusion for Cinematic Camera Motion Generation
Paper • 2607.03803 • Published • 12