Research map / Image generation / Text-to-image diffusion
AccDiffusion: An Accurate Method for Higher-Resolution Image Generation
Zhihang Lin, Mingbao Lin, Meng Zhao, Rongrong Ji
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 changed | Where | Measured | Effect |
|---|---|---|---|
| replace image-content-aware prompt with patch-content-aware prompts and add window interaction in dilated sampling | DemoFusion pipeline (AccDiffusion) · Laion-5B prompts, 4096x4096 | FID_r: 65.97 -> 63.89 | Improved |
| add patch-content-aware prompts (ablation) | AccDiffusion · 4096x4096 qualitative | object repetition (visual) | Improved |
| add window interaction in dilated sampling (ablation) | AccDiffusion · 4096x4096 qualitative | semantic consistency (visual) | Improved |
| remove text prompt during higher-resolution generation of DemoFusion (ablation) | DemoFusion · qualitative analysis | object repetition and detail | Mixed |
| remove residual connection and dilated sampling from DemoFusion (ablation) | DemoFusion · qualitative analysis | object repetition | Hurt |
| use per-word mean of attention map as binary mask threshold instead of a fixed threshold (ablation) | AccDiffusion · cross-attention statistics | word inclusion in patch prompt | Improved |
| vary patch prompt threshold c (very small vs very large) (ablation) | AccDiffusion · 4096x4096 qualitative | repetition vs detail | Mixed |
| generate beyond 6K resolution | AccDiffusion · indefinite extrapolation | detail quality | Hurt |
Later papers that compared with this method
4 later accepted papers report AccDiffusion as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.
- AccDiffusion v2: Toward More Accurate Higher-Resolution Diffusion Extrapolation (TPAMI 2025 · better on 9 of 11 shared results)
- FAM Diffusion: Frequency and Attention Modulation for High-Resolution Image Generation with Stable Diffusion (CVPR 2025 · better on 2 of 2 shared results)
- RepLDM: Reprogramming Pretrained Latent Diffusion Models for High-Quality, High-Efficiency, High-Resolution Image Generation (NeurIPS 2025 · better on 2 of 2 shared results)
- Is One GPU Enough? Pushing Image Generation at Higher-Resolutions with Foundation Models. (NeurIPS 2024 · better on 2 of 2 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DemoFusion — DemoFusion: Democratising High-Resolution Image Generation With No $$$ (CVPR 2024) · better on 8 of 9 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
- ResMaster: Mastering High-Resolution Image Generation via Structural and Fine-Grained Guidance (AAAI 2025 · similarity 0.86)
- ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models (ICLR 2024 · similarity 0.85)
- Hierarchical Patch Diffusion Models for High-Resolution Video Generation (CVPR 2024 · similarity 0.85)
- PatchVSR: Breaking Video Diffusion Resolution Limits with Patch-wise Video Super-Resolution (CVPR 2025 · similarity 0.84)
- DiffuseHigh: Training-Free Progressive High-Resolution Image Synthesis Through Structure Guidance (AAAI 2025 · similarity 0.84)
- More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Models (NeurIPS 2025 · similarity 0.84)
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.
