Downloads · 30 days
0
SiT-ReDi-XL-2
zelaki/SiT-ReDi-XL-2
SiT-ReDi-XL-2 is a unconditional image generation model from zelaki. Use it for the unconditional image generation task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Access
Public
Updated Oct 2, 2025
Repo size
10.8 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.ckpt10.8 GB · 100%
At a glance
- Task
- Unconditional Image Generation
- License
- apache-2.0
- Access
- Public
- Created
- Jun 2, 2025
- Updated
- Oct 2, 2025
- SHA
- da108b5e
Model card
From the Hugging Face model README
Boosting Generative Image Modeling via Joint Image-Feature Synthesis
Paper | Project Page | Code
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 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.
python sample.py SDE --image-size 256 --seed 42 --ckpt /path/to/ckpt
- Task
- Unconditional Image Generation
- License
- apache-2.0
- Created
- Jun 2, 2025
- Updated
- Oct 2, 2025