Research map / Image generation / Autoregressive and latent generation
ProcessMaker: A Generalized Process Visualization Framework with Adaptive Sequence Steps on Diffusion Transformers
Mengling Xu, Sisi You, Yaning Li, Bing-Kun Bao
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 |
|---|---|---|---|
| add sparse LoRA masks (single LoRA) (ablation) | MakeAnything base · Fabric Toys | CLIP alignment: 32.83 -> 33.03 | Improved |
| add sparse LoRA masks (single LoRA) (ablation) | MakeAnything base · Fabric Toys | trainable params: 4.19B -> 306.32M | Improved |
| add self-supervised representation alignment (ablation) | MakeAnything base · Fabric Toys | CLIP alignment: 32.83 -> 32.89 | No clear effect |
| add self-supervised representation alignment (ablation) | MakeAnything base · Fabric Toys | coherence: 4.60 -> 4.65 | Improved |
| add global frame difference in sliding window (ablation) | ProcessMaker stage 2 · Fabric Toys | CLIP alignment: 33.29 -> 33.61 | Improved |
| add local frame difference in sliding window (ablation) | ProcessMaker stage 2 · Fabric Toys | coherence: 4.70 -> 4.95 | Improved |
| add semantic frame difference in sliding window (ablation) | ProcessMaker stage 2 · Fabric Toys | CLIP alignment: 32.90 -> 33.61 | Improved |
| add semantic frame difference in sliding window (ablation) | ProcessMaker stage 2 · Fabric Toys | coherence: 4.95 -> 4.95 | No clear effect |
| use ProcessMaker instead of MakeAnything | multi-domain procedural generation · Icon | GPT-4o coherence: 3.50 -> 3.90 | Improved |
| use ProcessMaker instead of MakeAnything | multi-domain procedural generation · Painting | CLIP alignment: 34.24 -> 34.47 | Improved |
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.
- MakeAnything — MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation (CVPR 2026) · better on 7 of 7 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
- Diff-MoE: Diffusion Transformer with Time-Aware and Space-Adaptive Experts (ICML 2025 · similarity 0.83)
- Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation (ICML 2024 · similarity 0.83)
- Diffusion Transformer Captures Spatial-Temporal Dependencies: A Theory for Gaussian Process Data (ICLR 2025 · similarity 0.83)
- Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective (ICLR 2025 · similarity 0.82)
- Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch (NeurIPS 2025 · similarity 0.82)
- D-Flow: Differentiating through Flows for Controlled Generation (ICML 2024 · similarity 0.82)
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.
