Research map / Image generation / Text-to-image diffusion
Steered Diffusion: A Generalized Framework for Plug-and-Play Conditional Image Synthesis
Nithin Gopalakrishnan Nair, Anoop Cherian, Suhas Lohit, Ye Wang, Toshiaki Koike-Akino, Vishal M. Patel, Tim K. Marks
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 |
|---|---|---|---|
| steer implicit clean-image prediction x_0|t instead of noisy x_t | Steered Diffusion · CelebA face super-resolution | FID: 62.24 -> 51.19 | Improved |
| steer implicit prediction on semantic generation versus ILVR | Steered Diffusion · CelebA semantic layout to face | FID: 107.46 -> 41.38 | Improved |
| Steered Diffusion versus trained methods on semantic mIoU | Steered Diffusion · CelebA semantic layout to face | mIoU: 0.723 vs 0.532 | Hurt |
| use multi-step implicit modulation (iterate N times per timestep) | Steered Diffusion · inpainting and colorization | conditioning quality | Improved |
| use time-varying scaling factor k(t) instead of fixed | Steered Diffusion · semantic generation | sample realism | Improved |
| use very high or very low scaling factor K | Steered Diffusion · semantic generation | sample quality | Hurt |
| use a trained noise-robust inverse mapper instead of implicit denoised prediction | colorization · face colorization | detail preservation | Hurt |
| Steered Diffusion versus ILVR for colorization | Steered Diffusion · face colorization | FID: 67.66 -> 49.72 | Improved |
| Steered Diffusion versus PULSE on NIQE | Steered Diffusion · CelebA face super-resolution | NIQE: 5.04 vs 9.24 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- PULSE — PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models (CVPR 2020) · better on 1 of 2 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
- Plug-and-Play Diffusion Distillation (CVPR 2024 · similarity 0.90)
- CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image Generation (CVPR 2024 · similarity 0.90)
- A Simple Approach to Unifying Diffusion-based Conditional Generation (ICLR 2025 · similarity 0.90)
- Diffusion Self-Distillation for Zero-Shot Customized Image Generation (CVPR 2025 · similarity 0.90)
- R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation (ICLR 2024 · similarity 0.89)
- Dual Diffusion for Unified Image Generation and Understanding (CVPR 2025 · similarity 0.89)
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.
