AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

HiPrompt: Tuning-free Higher-Resolution Generation with Hierarchical MLLM Prompts

Xinyu Liu, Yingqing He, Lanqing Guo, Xiang Li, Bu Jin, Yan Li, Chi-Min Chan, Wei Xue, Wenhan Luo, Qifeng Liu, Yike Guo

IJCV 2026 · Image generation › Autoregressive and latent generation · approach: High-resolution diffusion synthesis · 19 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 hierarchical MLLM prompt guidance (ablation)SDXL-based DemoFusion baseline · 2048x4096FID_r: 1.21 decreaseImproved
add noise decomposition on top of MLLM prompts (ablation)HiPrompt · 2048x4096FID_c: 46.93 -> 35.17Improved
add both MLLM prompts and noise decomposition (ablation)baseline · 2048x4096FID_r: 76.24 -> 73.82Improved
add LLaVA prompts only (ablation)baseline · 4096x4096FID_c: 14.32 -> 11.82Improved
add ShareCaptioner prompts only (ablation)baseline · 4096x4096FID_c: 14.32 -> 8.80Improved
add noise decomposition to LLaVA prompts (ablation)HiPrompt · 4096x4096FID_r: 71.81 -> 70.40Improved
add noise decomposition to ShareCaptioner prompts (ablation)HiPrompt · 4096x4096FID_r: 71.01 -> 70.22Improved
swap LLaVA for ShareCaptioner as MLLM (ablation)HiPrompt · 4096x4096FID_c: 11.82 -> 8.80Improved
add N-grams refinement (ablation)HiPrompt with LLaVA · 2048x2048FID_r: 68.78 -> 67.79Improved
add LLaVA prompts only (no ND) (ablation)baseline · 4096x4096FID_r: 71.04 -> 71.81Hurt
HiPrompt vs DemoFusion at 16xHiPrompt · 4096x4096FID_c: 36.89 -> 43.60Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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