Energy-Guided Flow Matching
Paper • 2608.05811 • Published • 8
EG-FM Model Weights Access Application
Please complete this form to request access to the EG-FM model weights. Requests are reviewed manually.
Thank you for your interest in EG-FM. To support responsible use of the model weights, please provide accurate information below. Our team will normally review your request within 1 business days. Using an institutional, academic, or corporate email address may help us verify your application.
Log in or Sign Up to review the conditions and access this model content.
Energy-Guided Flow Matching (EG-FM)
Official checkpoints for Energy-Guided Flow Matching (EG-FM) on class-conditional ImageNet-1K generation at 256×256 and 512×512 resolutions.
EG-FM introduces an image-specific, energy-guided moving endpoint to construct an explicit coarse-to-fine generation trajectory while requiring no changes to the backbone or training data.
- Paper: Energy-Guided Flow Matching
- Code and usage: ysng123/EG-FM
Released models
| Model | Resolution | Training | FID |
|---|---|---|---|
| PixelDiT-200 | 256×256 | 200 epochs | 1.55 |
| PixelDiT-600 | 256×256 | 600 epochs | 1.45 |
| PixelDiT-220 | 512×512 | 200+20 epochs | 1.72 |
| PixelDiT-240 | 512×512 | 200+40 epochs | 1.68 |
All FID values use the ADM evaluation suite. The 512×512 models continue from the 200-epoch 256×256 checkpoint; 200+20 and 200+40 denote the initial training followed by additional high-resolution adaptation epochs.
For installation, checkpoint loading, inference, and evaluation commands, see the official GitHub repository.
License
The model weights are released under CC BY-NC 4.0. Commercial use is not permitted under this license.
Citation
@article{tong2026energy,
title = {Energy-Guided Flow Matching},
author = {Tong, Haoyang and He, Yu and Li, Fang and Ma, Lichen and Fu, Jingling and Chen, Dong and Chen, Zhen and Huang, Junshi and Cao, Jie},
journal = {arXiv preprint arXiv:2608.05811},
year = {2026}
}
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support