README.md

---
license: cc-by-nc-4.0
library_name: diffusers
pipeline_tag: text-to-image
tags:
- diffusers
- dit
- image-generation
- class-conditional
- imagenet
widget:
- output:
    url: DiT-XL-2-512/demo.png
language:
- en
---

# BiliSakura/DiT-diffusers

Diffusers-ready checkpoints for **Diffusion Transformers (DiT)**, re-packaged for local/offline use with a project-owned custom `DiTPipeline`.

> **Re-distribution notice:** weights and configs in this repo are re-distributed from [`facebook/DiT-XL-2-512`](https://huggingface.co/facebook/DiT-XL-2-512). Original work: [Scalable Diffusion Models with Transformers (ICCV 2023)](https://openaccess.thecvf.com/content/ICCV2023/html/Peebles_Scalable_Diffusion_Models_with_Transformers_ICCV_2023_paper.html). License: [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/).

This repo is derived from the development bundle in [Visual-Generative-Foundation-Model-Collection](https://github.com/Bili-Sakura/Visual-Generative-Foundation-Model-Collection). Inference only needs:

- This model repo (`BiliSakura/DiT-diffusers`)
- PyPI `diffusers`, `torch`, `safetensors`

## Important note

This repo intentionally does **not** use Diffusers built-in `diffusers.DiTPipeline`.
Instead, each model subfolder contains `pipeline.py` with a custom class named `DiTPipeline`.

## Available checkpoints

| Subfolder | Resolution | Source |
| --- | --- | --- |
| [`DiT-XL-2-256/`](DiT-XL-2-256/) | 256×256 | [`facebook/DiT-XL-2-256`](https://huggingface.co/facebook/DiT-XL-2-256) |
| [`DiT-XL-2-512/`](DiT-XL-2-512/) | 512×512 | [`facebook/DiT-XL-2-512`](https://huggingface.co/facebook/DiT-XL-2-512) |

Each subfolder is a self-contained Diffusers model repo with:

- `model_index.json` (includes ImageNet `id2label`)
- `pipeline.py` (custom `DiTPipeline`)
- `transformer/diffusion_pytorch_model.safetensors`
- `vae/diffusion_pytorch_model.safetensors`
- `scheduler/scheduler_config.json`

## Demo

![DiT-XL-2-512 demo](DiT-XL-2-512/demo.png)

```python
from pathlib import Path
import torch
from diffusers import DiffusionPipeline

model_dir = Path("path/to/DiT-XL-2-512")
pipe = DiffusionPipeline.from_pretrained(
    str(model_dir),
    local_files_only=True,
    custom_pipeline=str(model_dir / "pipeline.py"),
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
).to("cuda")
generator = torch.Generator(device="cuda").manual_seed(0)
out = pipe(
    class_labels=[207],
    num_inference_steps=250,
    guidance_scale=4.0,
    generator=generator,
).images[0]
out
```

## Repo layout

```text
BiliSakura/DiT-diffusers/
├── README.md
├── DiT-XL-2-256/
└── DiT-XL-2-512/
    ├── README.md
    ├── model_index.json
    ├── pipeline.py
    ├── demo.png
    ├── transformer/
    │   ├── config.json
    │   └── diffusion_pytorch_model.safetensors
    ├── vae/
    │   ├── config.json
    │   └── diffusion_pytorch_model.safetensors
    └── scheduler/
        └── scheduler_config.json
```