Research map / Image generation / Autoregressive and latent generation
Any-to-Any Generation via Composable Diffusion
Zineng Tang, Ziyi Yang, Chenguang Zhu, Michael Zeng, Mohit Bansal
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 CoDi instead of Versatile Diffusion for text-to-image synthesis | CoDi · COCO-caption validation | FID: 11.10 -> 11.26 | Hurt |
| Use CoDi instead of Make-A-Video for text-to-video generation | CoDi · MSR-VTT | CLIPSIM: 0.3049 -> 0.2890 | Hurt |
| Use CoDi instead of AudioLDM-L-Full for audio generation | CoDi · AudioCaps test | FD: 23.31 -> 22.90 | Improved |
| Use CoDi instead of AudioLDM-L-Full for audio generation | CoDi · AudioCaps test | IS: 8.13 -> 8.77 | Improved |
| Use CoDi instead of AudioLDM-L-Full for audio generation | CoDi · AudioCaps test | KL: 1.59 -> 1.40 | Improved |
| Use CoDi instead of AudioLDM-L-Full for audio generation | CoDi · AudioCaps test | FAD: 1.96 -> 1.80 | Improved |
| Use CoDi instead of AudioLDM-L-Full for audio generation | CoDi · AudioCaps test | OVL: 65.91 -> 66.87 | Improved |
| Use CoDi instead of AudioLDM-L-Full for audio generation | CoDi · AudioCaps test | REL: 65.97 -> 67.60 | Improved |
| Use CoDi instead of OFA for image captioning | CoDi · COCO image captioning | CIDEr: 154.9 -> 149.9 | Hurt |
| Use CoDi instead of AL-MixGen for audio captioning | CoDi · AudioCaps audio captioning | SPIDEr: 0.466 -> 0.480 | Improved |
| Use CoDi instead of AL-MixGen for audio captioning | CoDi · AudioCaps audio captioning | CIDEr: 0.755 -> 0.789 | Improved |
| Use CoDi instead of AL-MixGen for audio captioning | CoDi · AudioCaps audio captioning | SPICE: 0.177 -> 0.182 | Improved |
Closest papers by meaning
- CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image Generation (CVPR 2024 · similarity 0.87)
- CoDi-2: In-Context Interleaved and Interactive Any-to-Any Generation (CVPR 2024 · similarity 0.87)
- MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation (ICLR 2025 · similarity 0.87)
- DuoGen: Towards Autonomous Interleaved Multimodal Generation (CVPR 2026 · similarity 0.86)
- Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces (ICML 2025 · similarity 0.86)
- OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows (CVPR 2025 · similarity 0.86)
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.
