AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models

Nick Stracke, Stefan Andreas Baumann, Joshua Susskind, Miguel Angel Bautista, Bjorn Ommer

ECCV 2024 · Image generation › Text-to-image diffusion · approach: Text-driven synthesis and semantic guidance

Read the paper

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
use conditional LoRA instead of IP-Adapter for style conditioningSD 1.5 style adapter · COCO val style conditioningCLIP-T: 0.588 -> 0.637Improved
use LoRAdapter instead of IP-AdapterSD 1.5 style adapter · COCO val style conditioningCLIP-I: 0.828 -> 0.831Improved
use larger SDXL base with LoRAdapter instead of SD 1.5LoRAdapter style · COCO val style conditioningCLIP-I: 0.831 -> 0.849Improved
LoRAdapter vs from-scratch Open unCLIP on image similarityLoRAdapter style · COCO val style conditioningCLIP-I: 0.858 vs 0.831Hurt
use LoRAdapter-A (17M) instead of ControlNet for depthdepth structure adapter · COCO val depth conditioningMSE-d: 17.98 -> 17.27Improved
scale LoRAdapter from 17M to 32M by adapting every ResNet block (ablation)LoRAdapter depth · COCO val depth conditioningFID: 16.849 -> 15.670Improved
scale LoRAdapter from config A to B for HED (ablation)LoRAdapter HED · COCO val HED conditioningSSIM: 0.621 -> 0.644Improved
scale LoRAdapter from config A to B for HED (ablation)LoRAdapter HED · COCO val HED conditioningFID: 14.584 -> 14.761No clear effect
adapt cross-attention layers rather than self-attention or convolutional layers for style (ablation)style LoRAdapter · COCO val style conditioningqualitative fidelity/CLIPImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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