---
library_name: diffusers
tags:
- dit4sr
- super-resolution
- diffusion-transformer
base_model: stabilityai/stable-diffusion-3.5-medium
---
# dit4sr_custom_dataset

This repository contains the `checkpoint-190000` export from the local DiT4SR experiment `dit4sr_custom_dataset`.

## Included files

- `transformer/` contains the publishable model weights and config.
- `source_checkpoint.json` records the local source path and checkpoint name used for the upload.

## Loading

```python
from model_dit4sr.transformer_sd3 import SD3Transformer2DModel

model = SD3Transformer2DModel.from_pretrained("NisargUpadhyay/ImageSuperResolution-custom-dataset", subfolder="transformer")
```

You still need the rest of the DiT4SR codebase and the base SD3 assets described in this repository's README.