AI Paper Atlas

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

Zero-Shot Image Personalization from Personas

Harini S I, Somesh Singh, Yaman K Singla, David Doermann, Rajiv Shah

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Multi-subject personalization · 0 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 persona conditioning to LLM prompt rewriting14 LLMs · ZIP-BenchClipScore: gains 3% (Qwen3-30B-A3B) to 20% (Claude-Sonnet-4)Improved
Add persona conditioning (zero-shot)GPT-4o · ZIP-BenchPIGReward: 65.3 -> 73.4Improved
Use persona zero-shot instead of fine-tuned DrUMDrUM · benchmarks (3 of 4)CLIPScore: e.g. MovieLens 72.8 -> 76.4Improved
Use persona zero-shot instead of fine-tuned DrUMDrUM · PIPCLIPScore: 66.9 -> 60.2Hurt
Use ZIPPY 3-shot instead of TV 3-shotTV · ZIP-BenchCLIPScore: 62.4 -> 66.7Improved
Increase ZIPPY shots from 3 to 5ZIPPY · ZIP-BenchPIGReward: 77.5 -> 82.8Improved
Use persona conditioning instead of fine-tuning for pluralismViPer/DrUM · all usersCMMD: 0.55 / 0.31 -> 0.16Improved
Use persona conditioning for demographic alignment (IPF-normalized)DrUM · RapidData demographicsPIGReward: 56.8 -> 73.0Improved
Use MoE LLMs instead of dense Qwen3Qwen3-30B-A3B / 235B-A22B · ZIP-BenchClipScoreHurt

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