SiT ReDi XL 2

--- pipeline_tag: unconditional-image-generation license: apache-2.0 --- ## Boosting Generative Image Modeling via Joint Image-Feature Synthesis [Paper](https://arxiv.org/abs/2504.16064) | [Project Page](https://representationdiffusion.github.io/) | [Code](https://github.com/zelaki/ReDi) **ReDi** learns to generate coherent image-feature pairs from pure noise, significantly enhancing both generative quality and training efficiency. --- #### Model Description This model uses [SiT](https://github.com/willisma/SiT) as the base model. We train for 4M steps with a batch size of 256 on ImageNet 256x256. #### Metrics Generative performance on Imagenet Validation Set. | **Model** | **FID** | **SFID** | **IS** | **Prec** | **Rec** | |---------------------|---------|----------|--------|----------|---------| | **SiT-XL/2 w/ ReDi** | 1.64 | 4.63 | 289.3 | 0.65 | 0.77 | --- ## Sample Usage You can sample from our pre-trained ReDi models with `sample.py`. ```bash python sample.py SDE --image-size 256 --seed 42 --ckpt /path/to/ckpt ```

Source context: 0 downloads · 2 likes · Pipeline unconditional-image-generation · Repo zelaki/SiT-ReDi-XL-2