AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Memory-Efficient Fine-Tuning for Quantized Diffusion Model

Hyogon Ryu, Seohyun Lim, Hyunjung Shim

ECCV 2024 · Architectures and efficiency › Pruning and efficient tuning · approach: Adapter-based parameter-efficient tuning · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add multi-channel-wise scale update and 2 timestep experts to PEQA baseline (ablation)quantized DDIM on CIFAR-10 · CIFAR-10 unconditional (8-bit)FID: 4.39 -> 3.80Improved
add multi-channel-wise scale update to baseline (1 expert) (ablation)quantized DDIM on CIFAR-10 · CIFAR-10 unconditional (8-bit)FID: 4.39 -> 4.33Improved
add timestep-aware scales with 2 experts (no MCSU) (ablation)quantized DDIM on CIFAR-10 · CIFAR-10 unconditional (8-bit)FID: 4.39 -> 4.24Improved
increase timestep experts from 2 to 4 (with MCSU) (ablation)TuneQDM · CIFAR-10 unconditional (8-bit)FID: 3.80 -> 4.15Hurt
TuneQDM instead of baseline in 4-bit single-subject generationquantized Stable Diffusion · Single-subject generation (4-bit)DINO-I: 0.519 -> 0.551Improved
TuneQDM instead of baseline in 4-bit single-subject generationquantized Stable Diffusion · Single-subject generation (4-bit)CLIP-T: 0.313 -> 0.306Hurt
TuneQDM instead of baseline in 8-bit single-subject generationquantized Stable Diffusion · Single-subject generation (8-bit)DINO-I: 0.581 -> 0.578No clear effect
TuneQDM instead of baseline in multi-subject generation (4-bit)quantized Stable Diffusion · Multi-subject generation (4-bit)DINO-I: 0.275 -> 0.276No clear effect
TuneQDM vs QLoRA on CIFAR-10quantized DDIM · CIFAR-10 unconditional (8-bit)FID: 4.15 -> 3.80 (QLoRA r=2 vs TuneQDM)Improved
TuneQDM extra scale multiplications at inference4-bit linear layers · Linear-layer inference timetime (s): 6.94 -> 6.99Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy