verl-omni
by verl-project · GitHub
Multimodal RL training framework for diffusion & omni models
⭐ Stars
599
🍴 Forks
84
🔥 Trending
+6 today
📜 License
Apache-2.0
Commercial use OK📅 Created
2026
🔄 Last commit
2 days ago
🏷️ Category
diffusion-models
💻 Language
You maintain this project?
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
📈 Star history
2026-07-202026-07-21
📄 About
Multimodal RL training framework for diffusion & omni models
❓ Frequently asked questions
What is verl-omni?
Multimodal RL training framework for diffusion & omni models
Is verl-omni open source?
verl-omni is an open-source project. It is released under the Apache-2.0 license.
Is verl-omni free?
Yes. verl-omni is free and open source — you can use, modify and self-host it.
🏅 Maintainer of this project?
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://opensourceai.tech/project/verl-project-verl-omni.html)
🧬 Shares DNA with🧬 View the DNA map →
MeanFlow
PyTorch implementation of MeanFlow & iMF (one-step generative modeling).
★ 1.2k · diffusion-models
sharesflow-matchingdiffusion-models
VLM-R1
Solve Visual Understanding with Reinforced VLMs
★ 6k · deepseek-r1
sharesgrpomultimodal
Pyramid-Flow
[ICLR 2025] Pyramidal Flow Matching for Efficient Video Generative Modeling
★ 3.2k · diffusion-models
sharesflow-matchingdiffusion-models
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.