VDE accelerates rectified flow models like Flux by 3.22x with LPIPS of 0.069 via velocity decomposition into parallel/orthogonal components plus periodic full-pass anchoring.
Mobilediffusion: Subsecond text-to-image generation on mobile devices.arXiv preprint arXiv:2311.16567, 2(3):4
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.CV 5verdicts
UNVERDICTED 5representative citing papers
DSA adds a jointly trained confidence head to autoregressive video diffusion models that dynamically allocates fewer or more denoising steps per frame, achieving 22.63 FPS real-time generation on H100 while matching VBench quality.
ElasticDiT introduces an elastic DiT architecture with adjustable spatial compression and block depth plus Shift Sparse Block Attention and a distilled VAE to enable a single model to cover multiple fidelity-latency points for high-resolution image generation on mobile devices.
Elastic Looped Transformers share weights across recurrent blocks and apply intra-loop self-distillation to deliver 4x parameter reduction while matching competitive FID and FVD scores on ImageNet and UCF-101.
Sana-0.6B produces high-resolution images with strong text alignment at 20x smaller size and 100x higher throughput than Flux-12B by combining 32x image compression, linear DiT blocks, and a decoder-only LLM text encoder.
citing papers explorer
-
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers
Sana-0.6B produces high-resolution images with strong text alignment at 20x smaller size and 100x higher throughput than Flux-12B by combining 32x image compression, linear DiT blocks, and a decoder-only LLM text encoder.