Research map / Image generation / Fast diffusion sampling
A-FloPS: Accelerating Diffusion Models via Adaptive Flow Path Sampler
Cheng Jin, Zhenyu Xiao, Yuantao Gu
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 |
|---|---|---|---|
| reparameterize diffusion trajectory into flow-matching form (FloPS) vs DDIM (ablation) | DiT sampler · ImageNet 256 (DiT, CFG 1.5), NFE 5 | FID: 38.12 -> 14.9 | Improved |
| same, at NFE 10 (ablation) | DiT sampler · ImageNet 256 (DiT, CFG 1.5), NFE 10 | FID: 6.234 -> 4.11 | Improved |
| add adaptive velocity decomposition on top of FloPS (ablation) | FloPS · ImageNet 256 (DiT, CFG 1.5), NFE 5 | FID: 14.9 -> 6.977 | Improved |
| A-FloPS vs UniPC | DiT sampler · ImageNet 256 (DiT, CFG 1.5), NFE 5 | FID: 19.165 -> 6.977 | Improved |
| A-FloPS vs UniPC at NFE 10 | DiT sampler · ImageNet 256 (DiT, CFG 1.5), NFE 10 | FID: 4.638 -> 3.440 | Improved |
| add adaptive mechanism to native flow model Euler | SD3.5 Euler · COCO prompts, NFE 5 | ImageReward: 0.300 -> 0.579 | Improved |
| add adaptive mechanism to native flow model Euler | SD3.5 Euler · COCO prompts, NFE 9 | CLIP score: 0.319 -> 0.317 | Hurt |
| add adaptive mechanism to Euler | SD3.5 Euler · COCO prompts, NFE 9 | GPT preference: 0.315 -> 0.685 | Mixed |
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.
- UniPC — UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models (NeurIPS 2023) · better on 6 of 6 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
- Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch (NeurIPS 2025 · similarity 0.91)
- Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference (NeurIPS 2024 · similarity 0.91)
- Tortoise and Hare Guidance: Accelerating Diffusion Model Inference with Multirate Integration (NeurIPS 2025 · similarity 0.90)
- Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow (ICLR 2025 · similarity 0.90)
- A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models (ICML 2024 · similarity 0.90)
- Test-time Scaling of Diffusions with Flow Maps (NeurIPS 2026 · similarity 0.90)
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.
