---
license: mit
base_model: bytedance-research/GRN
pipeline_tag: text-to-image
tags:
- safetensors
- text-to-image
---

# GRN 2B text-to-image — safetensors conversion

An unofficial conversion of the **GRN** (Generative Refinement Networks) 2B text-to-image
checkpoint and its HBQ tokenizer from PyTorch pickles to safetensors. The weights are
ByteDance's; nothing was retrained or modified.

- Official weights: [bytedance-research/GRN](https://huggingface.co/bytedance-research/GRN)
- Official code: [MGenAI/GRN](https://github.com/MGenAI/GRN)
- Paper: [arXiv 2604.13030](https://arxiv.org/abs/2604.13030)

For anything about the model itself — usage, training, results, citation — see the official
pages above.

## Files

| File | Converted from | Notes |
|---|---|---|
| `grn-t2i-2b-bf16.safetensors` | `GRN_T2I_2B_FSA_251600.pth` | the transformer, cast to BF16 |
| `grn-hbq-tokenizer.safetensors` | `HBQ_image_video_tokenizer_64dim_M4_20260626.ckpt` | the tokenizer (EMA weights), as stored |
| `grn_convert.py` | | the script used |

Tensor names are unchanged. The text encoder (umT5-XXL) is not included; use the one from the
official repository or any standard umT5-XXL encoder.

## Conversion

Done on the CPU with `torch.load(..., weights_only=True)`, keeping tensors only:

```bash
python grn_convert.py GRN_T2I_2B_FSA_251600.pth grn-t2i-2b-bf16.safetensors bf16
python grn_convert.py HBQ_image_video_tokenizer_64dim_M4_20260626.ckpt grn-hbq-tokenizer.safetensors
```

## License

MIT, as the original release.