Research map / Image generation / Text-to-image diffusion
RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths
Zeyue Xue, Guanglu Song, Qiushan Guo, Boxiao Liu, Zhuofan Zong, Yu Liu, Ping Luo
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 |
|---|---|---|---|
| use RAPHAEL instead of DeepFloyd | MS-COCO 256×256 zero-shot image generation · MS-COCO 256×256 zero-shot | zero-shot FID-30k: 6.66 -> 6.61 | Improved |
| add space-MoE (ablation) | RAPHAEL · RAPHAEL ablation | CLIP score | Improved |
| add space-MoE (ablation) | RAPHAEL · RAPHAEL ablation | FID | Improved |
| add edge-supervised learning (ablation) | RAPHAEL · RAPHAEL ablation | image quality | Improved |
| add time-MoE (ablation) | RAPHAEL · RAPHAEL ablation | image quality | Improved |
| set the space-MoE threshold α to 0.2 (ablation) | RAPHAEL · RAPHAEL ablation | performance: 0.2 | Improved |
| set the edge-supervision timestep threshold Tc to 500 (ablation) | RAPHAEL · RAPHAEL ablation | texture learning: 500 | Improved |
| increase the number of space experts (ablation) | RAPHAEL · RAPHAEL ablation | FID | Improved |
| use 6 space experts (ablation) | RAPHAEL · RAPHAEL ablation | inference speed: 24% | Hurt |
Later papers that compared with this method
6 later accepted papers report RAPHAEL as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Bridge Diffusion Model: Bridge Chinese Text-to-Image Diffusion Model with English Communities (AAAI 2025 · better on 0 of 1 shared result)
- Learning Visual Generative Priors without Text (CVPR 2025 · better on 1 of 1 shared result)
- Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens (ICLR 2025 · better on 1 of 1 shared result)
- Paragraph-to-Image Generation with Information-Enriched Diffusion Model (IJCV 2025 · better on 0 of 1 shared result)
- PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis (ICLR 2024 · better on 0 of 1 shared result)
- PanGu-Draw: Advancing Resource-Efficient Text-to-Image Synthesis with Time-Decoupled Training and Reusable Coop-Diffusion (ECCV 2024 · better on 0 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- ERNIE-ViLG 2.0 — ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model With Knowledge-Enhanced Mixture-of-Denoising-Experts (CVPR 2023) · better on 1 of 1 shared result
- Muse-3B — Muse: Text-To-Image Generation via Masked Generative Transformers (ICML 2023) · better on 1 of 1 shared result
- GLIDE — GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models (ICML 2022) · better on 1 of 1 shared result
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
- Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models (AAAI 2025 · similarity 0.90)
- PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis (ICLR 2024 · similarity 0.89)
- Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis (CVPR 2025 · similarity 0.89)
- InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation (ICLR 2024 · similarity 0.88)
- SemanticDraw: Towards Real-Time Interactive Content Creation from Image Diffusion Models (CVPR 2025 · similarity 0.88)
- Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models (CVPR 2024 · similarity 0.88)
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.
