REVIEW 8 cited by
EdgeFusion: On-Device Text-to-Image Generation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
The intensive computational burden of Stable Diffusion (SD) for text-to-image generation poses a significant hurdle for its practical application. To tackle this challenge, recent research focuses on methods to reduce sampling steps, such as Latent Consistency Model (LCM), and on employing architectural optimizations, including pruning and knowledge distillation. Diverging from existing approaches, we uniquely start with a compact SD variant, BK-SDM. We observe that directly applying LCM to BK-SDM with commonly used crawled datasets yields unsatisfactory results. It leads us to develop two strategies: (1) leveraging high-quality image-text pairs from leading generative models and (2) designing an advanced distillation process tailored for LCM. Through our thorough exploration of quantization, profiling, and on-device deployment, we achieve rapid generation of photo-realistic, text-aligned images in just two steps, with latency under one second on resource-limited edge devices.
Forward citations
Cited by 8 Pith papers
-
SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices
A compact elastic diffusion transformer with adaptive sparse attention and knowledge-guided distribution-matching distillation achieves 4-step 1K image generation on a phone in roughly 1.8 seconds.
-
On-device Sora: Enabling Training-Free Diffusion-based Text-to-Video Generation for Mobile Devices
A training-free pipeline makes diffusion text-to-video generation run on an iPhone 15 Pro with quality close to GPU output, at the cost of slower generation.
-
SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training
SnapGen is a 379M-parameter UNet with cross-architecture distillation and a 1.38M-parameter decoder that generates 1024x1024 images on a phone in about 1.4 seconds, with GenEval 0.66 and ImageNet FID 2.06.
-
MoViE: Mobile Diffusion for Video Editing
MoViE distills a diffusion-based video editor into a single-step mobile model, achieving 12 fps on a Snapdragon 8 Gen 3 phone with modest quality loss.
-
Individual Content and Motion Dynamics Preserved Pruning for Video Diffusion Models
A block-pruning plus distillation method for video diffusion models, VDMini, achieves 1.25x to 2.5x speedups with modest quality loss across three video generation models.
-
Adversarial Diffusion Compression for Real-World Image Super-Resolution
AdcSR distills OSEDiff into a pruned diffusion-GAN that cuts inference time 3.7x and parameters 74% while achieving comparable super-resolution quality.
-
Contract-Inspired Contest Theory for Controllable Image Generation in Mobile Edge Metaverse
A contract-inspired contest mechanism combined with diffusion-model DRL is used to set transmit powers for controllable image generation in mobile edge Metaverse, with claims of improved image quality and convergence.
-
Robust Single-Stage Fully Sparse 3D Object Detection via Detachable Latent Diffusion
The submitted manuscript's abstract and full text are mismatched; the claimed 3D detection method is not present in the body.
Discussion (0). Continue with ORCID to comment.