REVIEW 8 cited by
BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
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
read the original abstract
Diffusion-based image generation models have achieved great success in recent years by showing the capability of synthesizing high-quality content. However, these models contain a huge number of parameters, resulting in a significantly large model size. Saving and transferring them is a major bottleneck for various applications, especially those running on resource-constrained devices. In this work, we develop a novel weight quantization method that quantizes the UNet from Stable Diffusion v1.5 to 1.99 bits, achieving a model with 7.9X smaller size while exhibiting even better generation quality than the original one. Our approach includes several novel techniques, such as assigning optimal bits to each layer, initializing the quantized model for better performance, and improving the training strategy to dramatically reduce quantization error. Furthermore, we extensively evaluate our quantized model across various benchmark datasets and through human evaluation to demonstrate its superior generation quality.
Forward citations
Cited by 8 Pith papers
-
DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization
A post-training quantization method that combines learned channel scaling and power-of-two scaling keeps diffusion image quality high at 4-bit weight, 6-bit activation precision.
-
DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion Models
DGQ quantizes text-to-image diffusion models to 4-8 bits without fine-tuning by preserving activation outliers and applying prompt-specific log quantization to cross-attention scores.
-
1.58-bit FLUX
A post-training method reduces 99.5% of FLUX.1-dev's transformer weights to ternary values and reports roughly comparable text-to-image quality with large storage and memory savings.
-
FADA: Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillation
FADA distills a diffusion-based talking avatar model into a 6-step student that mimics multi-condition classifier-free guidance with learnable tokens, achieving 4.17 to 12.5 times NFE speedup with comparable quality.
-
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.
-
HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Diffusion
Training-free sparse attention for video DiTs cuts latency up to ~2.1× via 3D local-window clustering, hybrid step updates, and hardware-aware cluster merging while improving fidelity over prior sparse methods.
-
WhisperKit: On-device Real-time ASR with Billion-Scale Transformers
WhisperKit's optimized on-device Whisper Large v3 Turbo streaming system reportedly achieves 0.46 s per-word latency and 2.2% WER, beating cloud baselines in its benchmark.
-
Efficiency Meets Fidelity: A Novel Quantization Framework for Stable Diffusion
A serial-to-parallel distillation pipeline with per-timestep activation quantization makes W4A8 quantized Stable Diffusion models generate images much closer to the full-precision model than prior PTQ methods.
Discussion (0). Continue with ORCID to comment.