---
license: apache-2.0
library_name: diffusers
pipeline_tag: unconditional-image-generation
tags:
- diffusers
- priming
- image-generation
- class-conditional
- one-step
- imagenet
widget:
- text: golden retriever
  output:
    url: demo.png
language:
- en
---

# Priming-diffusers

Native [diffusers](https://github.com/huggingface/diffusers) checkpoints for **Priming** ([Are We Overthinking One-Step Generation?](https://arxiv.org/abs/2610.20331)). Code: [JaeyeonKim01/priming](https://github.com/JaeyeonKim01/priming). Each variant folder is self-contained:

- `pipeline.py` — `PrimingPipeline`
- `scheduler/scheduling_priming.py` — `PrimingScheduler` (one evaluation; the transformer predicts the clean image)
- `transformer/transformer_priming.py` — `PrimingTransformer2DModel`

Load with PyPI `diffusers` and `trust_remote_code=True`. No extra Priming package is required. Sampling is one forward pass in RGB at 256×256 with `guidance_scale=1`. Weights are the released post-training EMA. The paper reports ImageNet-256 FID 1.38 for Priming-B and 1.19 for Priming-L.

## Available checkpoints

| Checkpoint | Path | Resolution | Steps | Guidance |
| --- | --- | --- | ---: | ---: |
| Priming-B | [`Priming-B/`](Priming-B/) | 256×256 | 1 | 1.0 |
| Priming-L | [`Priming-L/`](Priming-L/) | 256×256 | 1 | 1.0 |

## Demo

![Priming-B demo](demo.png)

Class: *golden retriever* (ImageNet 207) — 256×256, 1 step, `guidance_scale=1.0`, `torch_dtype=bfloat16`, seed 1.

## ImageNet class labels

Each variant keeps an English `id2label` map in `model_index.json`.

- `pipe.id2label` — id → English label
- `pipe.labels` — synonym → id
- `pipe.get_label_ids("golden retriever")`
- `pipe(class_labels="golden retriever", ...)` — string labels resolve automatically

`height` and `width` default to 256. Other sizes divisible by the patch size of 16 interpolate the learned positions and rebuild 2-D rotary frequencies.

## Inference

```python
import torch
from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained(
    "BiliSakura/Priming-diffusers",
    subfolder="Priming-B",  # or "Priming-L"
    custom_pipeline="pipeline.py",
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
).to("cuda")

print(pipe.id2label[207])
image = pipe(
    class_labels="golden retriever",
    num_inference_steps=1,
    guidance_scale=1.0,
    generator=torch.Generator(device="cuda").manual_seed(1),
).images[0]
image.save("demo.png")
```

Local checkout:

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

model_dir = Path("Priming-diffusers/Priming-B")
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")
```

## Citation

```bibtex
@misc{park2026are,
  title   = {Are We Overthinking One-Step Generation?},
  author  = {Park, Woobin and Kim, Jaeyeon and Du, Yilun and Chen, Sitan and Han, Bohyung},
  year    = {2026},
  eprint  = {2610.20331},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url     = {https://arxiv.org/abs/2610.20331}
}
```