README.md

---
license: apache-2.0
library_name: diffusers
pipeline_tag: text-to-image
base_model: shallowdream204/BitDance-14B-64x
language:
  - en
tags:
  - bitdance
  - text-to-image
  - custom-pipeline
  - diffusers
  - qwen
---

# BitDance-14B-64x (Diffusers)

Diffusers-converted checkpoint for BitDance-14B-64x with bundled custom pipeline code (`bitdance_diffusers`) for direct loading with `DiffusionPipeline`.

## Quickstart (native diffusers)

```python
import torch
from diffusers import DiffusionPipeline

repo_id = "BiliSakura/BitDance-14B-64x-diffusers"

pipe = DiffusionPipeline.from_pretrained(
    repo_id,
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
).to("cuda")

result = pipe(
    prompt="A cinematic landscape photo of snowy mountains at sunrise.",
    height=1024,
    width=1024,
    num_inference_steps=50,
    guidance_scale=7.5,
)
result.images[0].save("bitdance_14b_64x.png")
```

## Model Metadata

- Pipeline class: `BitDanceDiffusionPipeline`
- Diffusers version in config: `0.36.0`
- Parallel prediction factor: `64`
- Text stack: `Qwen3ForCausalLM` + `Qwen2TokenizerFast`
- Supported resolutions include `1024x1024`, `1280x768`, `768x1280`, `2048x512`, and more (see `model_index.json`)

## Citation

If you use this model, please cite BitDance and Diffusers:

```bibtex
@article{ai2026bitdance,
  title   = {BitDance: Scaling Autoregressive Generative Models with Binary Tokens},
  author  = {Ai, Yuang and Han, Jiaming and Zhuang, Shaobin and Hu, Xuefeng and Yang, Ziyan and Yang, Zhenheng and Huang, Huaibo and Yue, Xiangyu and Chen, Hao},
  journal = {arXiv preprint arXiv:2602.14041},
  year    = {2026}
}

@inproceedings{von-platen-etal-2022-diffusers,
  title     = {Diffusers: State-of-the-art diffusion models},
  author    = {Patrick von Platen and Suraj Patil and Anton Lozhkov and Damar Jablonski and Hernan Bischof and Thomas Wolf},
  booktitle = {GitHub repository},
  year      = {2022},
  url       = {https://github.com/huggingface/diffusers}
}
```

## License

This repository is distributed under the Apache-2.0 license, consistent with the upstream BitDance release.