AI Paper Atlas

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

PreciseControl: Enhancing Text-To-Image Diffusion Models with Fine-Grained Attribute Control

Rishubh Parihar, Sachidanand VS, Sabariswaran Mani, Tejan Karmali, Venkatesh Babu RADHAKRISHNAN

ECCV 2024 · Image generation › Text-to-image diffusion · approach: Multi-subject personalization · 18 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
condition T2I on StyleGAN W+ latent edit direction instead of text prompt for attribute editing (ablation)PreciseControl · Attribute editing (Beard, Age)Delta CLIP: Beard 0.986 -> 2.473; Age 0.429 -> 1.777Improved
use W+ latent editing instead of text-based Imagic editingPreciseControl · Attribute editing (Beard)LPIPS: 0.533 -> 0.185Improved
use W+ latent editing instead of Imagic for identity preservationPreciseControl · Attribute editing (Beard)identity similarity (CS): 0.492 -> 0.731Improved
delay identity token injection until timestep below tau (ablation)PreciseControl · personalization (qualitative)text editabilityImproved
add time-dependent token embeddings (ablation)PreciseControl latent adaptor · personalization (qualitative)identity similarityImproved
add subject-specific LoRA tuning (ablation)PreciseControl · personalization (qualitative)identity and prompt similarityImproved
add identity loss and regularization loss (ablation)PreciseControl · personalization (qualitative)identity/editabilityImproved
separate subject-specific LoRA models fused with masks instead of joint training (ablation)multi-subject composition · multi-subject generation (qualitative)attribute mixingImproved
use text-based Imagic editing vs W+ for edit strengthImagic · Attribute editing (Smile)Delta CLIP: Imagic 1.945 vs Ours + W+ 1.104Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 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